From 6dc9484d8f842c60a25003cc3b73f8fba6ab03a2 Mon Sep 17 00:00:00 2001 From: Chris Nestrud Date: Mon, 21 Sep 2026 18:44:56 -0500 Subject: [PATCH 01/10] Silence provider model-list fetch connection errors The /model command fetches provider model lists as a best-effort HTTP request and printed an error whenever the endpoint was unreachable, e.g. no local Ollama server at localhost:11434. Suppress connection errors so an absent endpoint contributes no models, while keeping the diagnostic print for real fetch failures. --- cecli/helpers/model_providers.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/cecli/helpers/model_providers.py b/cecli/helpers/model_providers.py index 0b2f29b1d80..72bb7c5e82b 100644 --- a/cecli/helpers/model_providers.py +++ b/cecli/helpers/model_providers.py @@ -399,6 +399,10 @@ def _fetch_provider_models(self, provider: str) -> Optional[Dict]: ) response.raise_for_status() return response.json() + except requests.exceptions.ConnectionError: + # Unreachable endpoint (e.g. no local Ollama server at + # localhost:11434): stay silent and contribute no models. + return None except Exception as ex: print(f"Failed to fetch {provider} model list: {ex}") return None From a267e017930448468fad00512bd589682a1667ab Mon Sep 17 00:00:00 2001 From: Chris Nestrud Date: Tue, 22 Sep 2026 17:32:11 -0500 Subject: [PATCH 02/10] fix(mcp): pass the session read timeout in the type the installed mcp SDK expects mcp SDK 2.x types ClientSession.read_timeout_seconds as a float number of seconds and adds it to other floats internally, so the timedelta that 1.x wanted made every HTTP MCP server fail to initialize with "unsupported operand type(s) for +: float and datetime.timedelta". Return whichever type the installed major wants so both stay connected. Adds unit coverage for the 1.x and 2.x branches in tests/mcp/test_server_sdk_compat.py. --- cecli/mcp/server.py | 20 +++++++++++++++++++- tests/mcp/test_server_sdk_compat.py | 19 +++++++++++++++++++ 2 files changed, 38 insertions(+), 1 deletion(-) diff --git a/cecli/mcp/server.py b/cecli/mcp/server.py index c3758e76a55..bb3cf4fc279 100644 --- a/cecli/mcp/server.py +++ b/cecli/mcp/server.py @@ -337,7 +337,9 @@ async def _enter_client_session(self, read, write): ClientSession( read, write, - read_timeout_seconds=timedelta(seconds=self._request_timeout_seconds()), + read_timeout_seconds=_client_session_read_timeout( + self._request_timeout_seconds() + ), ) ) await session.initialize() @@ -732,3 +734,19 @@ def _unpack_transport(transport): """ read, write = transport[0], transport[1] return read, write + + +def _client_session_read_timeout(seconds: float) -> timedelta | float: + """Return a read timeout in the form the installed mcp SDK expects. + + mcp SDK 1.x types ``ClientSession.read_timeout_seconds`` as a + ``timedelta``; SDK 2.x types it as a float number of seconds and adds it to + other floats internally, so a ``timedelta`` raises ``TypeError: + unsupported operand type(s) for +: 'float' and 'datetime.timedelta'`` at + connect time. Return whichever type the installed SDK wants, so both majors + keep the same per-request timeout instead of failing to connect. + """ + if _get_mcp_major_version() >= 2: + return seconds + + return timedelta(seconds=seconds) diff --git a/tests/mcp/test_server_sdk_compat.py b/tests/mcp/test_server_sdk_compat.py index abe7dcafe7f..1f274c99174 100644 --- a/tests/mcp/test_server_sdk_compat.py +++ b/tests/mcp/test_server_sdk_compat.py @@ -6,12 +6,14 @@ static headers are configured). """ +from datetime import timedelta from unittest.mock import AsyncMock, MagicMock, patch import pytest from cecli.mcp.server import ( HttpStreamingServer, + _client_session_read_timeout, _get_http_client_module, _get_mcp_major_version, _get_oauth_callback_handler, @@ -77,6 +79,23 @@ def test_unpack_transport_mcp2_two_tuple(monkeypatch): assert (read, write) == ("r", "w") +def test_client_session_read_timeout_timedelta_for_mcp1(monkeypatch): + """mcp 1.x types the session read timeout as a timedelta.""" + monkeypatch.setattr("cecli.mcp.server._get_mcp_major_version", lambda: 1) + + assert _client_session_read_timeout(120.0) == timedelta(seconds=120) + + +def test_client_session_read_timeout_float_for_mcp2(monkeypatch): + """mcp 2.x types the session read timeout as a float number of seconds.""" + monkeypatch.setattr("cecli.mcp.server._get_mcp_major_version", lambda: 2) + + timeout = _client_session_read_timeout(120.0) + + assert timeout == 120.0 + assert not isinstance(timeout, timedelta) + + @pytest.mark.asyncio async def test_oauth_callback_handler_mcp1_passthrough(monkeypatch): """mcp 1.x uses the raw callback returning an (auth_code, state) tuple.""" From 88eedcdfe78b6b55db069594508d099fa26735b0 Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 19:20:42 -0400 Subject: [PATCH 03/10] Update Model Metadata --- cecli/resources/model-metadata.ext.json | 32 + cecli/resources/model-metadata.json | 26465 ++++++++++++++-------- 2 files changed, 16474 insertions(+), 10023 deletions(-) diff --git a/cecli/resources/model-metadata.ext.json b/cecli/resources/model-metadata.ext.json index b203cd615ce..1774ca20027 100644 --- a/cecli/resources/model-metadata.ext.json +++ b/cecli/resources/model-metadata.ext.json @@ -374,6 +374,38 @@ "supports_parallel_function_calling": true, "supports_response_schema": true }, + "github_copilot/gpt-6-luna": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "source": "https://docs.github.com/en/copilot/reference/ai-models/supported-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-sol": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "source": "https://docs.github.com/en/copilot/reference/ai-models/supported-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, "github_copilot/grok-4.6": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, diff --git a/cecli/resources/model-metadata.json b/cecli/resources/model-metadata.json index 632baf441da..a3d66916707 100644 --- a/cecli/resources/model-metadata.json +++ b/cecli/resources/model-metadata.json @@ -47,990 +47,1194 @@ "output_cost_per_token": 7e-7, "supports_system_messages": true }, - "amazon-nova/nova-lite-v1": { - "input_cost_per_token": 6e-8, - "litellm_provider": "amazon_nova", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/agnes-2.5-flash": { + "input_cost_per_token": 3e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 512000, + "max_output_tokens": 65500, + "max_tokens": 65500, "mode": "chat", - "output_cost_per_token": 2.4e-7, - "supports_function_calling": true, - "supports_pdf_input": true, + "output_cost_per_token": 1.5e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/agnes-2.5-pro": { + "cache_read_input_token_cost": 3.78e-9, + "input_cost_per_token": 4.5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_reasoning": true, "supports_vision": true }, - "amazon-nova/nova-micro-v1": { - "input_cost_per_token": 3.5e-8, - "litellm_provider": "amazon_nova", - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/cc-glm-5.1": { + "input_cost_per_token": 6e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.4e-7, + "output_cost_per_token": 2.2e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true }, - "amazon-nova/nova-premier-v1": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "amazon_nova", + "aihubmix/claude-fable-5": { + "cache_read_input_token_cost": 0.0000011, + "cache_creation_input_token_cost": 0.00001375, + "input_cost_per_token": 0.000011, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000125, + "output_cost_per_token": 0.000055, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_sampling_params": false }, - "amazon-nova/nova-pro-v1": { - "input_cost_per_token": 8e-7, - "litellm_provider": "amazon_nova", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/claude-haiku-4-5": { + "cache_read_input_token_cost": 1.1e-7, + "cache_creation_input_token_cost": 0.000001375, + "input_cost_per_token": 0.0000011, + "litellm_provider": "aihubmix", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000032, + "output_cost_per_token": 0.0000055, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 4096 }, - "amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", + "aihubmix/claude-opus-4-8-think": { + "cache_read_input_token_cost": 5e-7, + "cache_creation_input_token_cost": 0.00000625, + "input_cost_per_token": 0.000005, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000025, + "output_cost_per_token": 0.000025, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false }, - "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-7, - "input_cost_per_token": 0.0000021875, - "input_cost_per_image_token": 0.0000021875, - "input_cost_per_audio_token": 0.0000021875, - "litellm_provider": "bedrock_converse", + "aihubmix/claude-opus-5": { + "cache_read_input_token_cost": 5e-7, + "cache_creation_input_token_cost": 0.00000625, + "input_cost_per_token": 0.000005, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000175, + "output_cost_per_token": 0.000025, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_sampling_params": false }, - "amazon.nova-lite-v1:0": { - "input_cost_per_token": 6e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/claude-sonnet-5": { + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 0.0000025, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.4e-7, + "output_cost_per_token": 0.00001, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "prompt_cache_min_tokens": 1024, + "supports_adaptive_thinking": true, + "supports_sampling_params": false }, - "amazon.nova-micro-v1:0": { - "input_cost_per_token": 3.5e-8, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/coding-glm-5.3": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 6e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.4e-7, + "output_cost_per_token": 2.2e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_response_schema": true }, - "amazon.nova-pro-v1:0": { - "input_cost_per_token": 8e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "max_tokens": 10000, + "aihubmix/coding-kimi-k3": { + "cache_read_input_token_cost": 6.6e-8, + "input_cost_per_token": 4.4e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 0.0000032, + "output_cost_per_token": 0.00000161333, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true + "supports_vision": true }, - "amazon.titan-text-express-v1": { - "input_cost_per_token": 0.0000013, - "litellm_provider": "bedrock", - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "max_tokens": 8000, + "aihubmix/coding-xiaomi-mimo-v2-omni": { + "cache_read_input_token_cost": 1.6e-8, + "input_cost_per_token": 8e-8, + "litellm_provider": "aihubmix", "mode": "chat", - "output_cost_per_token": 0.0000017 + "output_cost_per_token": 4e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "amazon.titan-text-lite-v1": { - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "aihubmix/coding-xiaomi-mimo-v2.5": { + "cache_read_input_token_cost": 1.6e-9, + "input_cost_per_token": 8e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 4e-7 + "output_cost_per_token": 1.6e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "amazon.titan-text-premier-v1:0": { - "input_cost_per_token": 5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "aihubmix/coding-xiaomi-mimo-v2.5-pro": { + "cache_read_input_token_cost": 1.6e-9, + "input_cost_per_token": 2e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000015 + "output_cost_per_token": 4e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true }, - "anthropic.claude-3-5-haiku-20241022-v1:0": { - "cache_creation_input_token_cost": 0.000001, - "cache_read_input_token_cost": 8e-8, - "input_cost_per_token": 8e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/command-a-plus-05-2026": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "aihubmix", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.00001, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "prompt_cache_min_tokens": 2048 + "supports_vision": true }, - "anthropic.claude-3-5-sonnet-20240620-v1:0": { - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", + "aihubmix/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.84e-8, + "input_cost_per_token": 1.42e-7, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 2.84e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.00003, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7 + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true }, - "anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", + "aihubmix/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.4027e-7, + "input_cost_per_token": 0.00000169, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00000338, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/doubao-seed-2-0-code-preview": { + "cache_read_input_token_cost": 9.644e-8, + "input_cost_per_token": 4.822e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002411, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.00003, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7 + "supports_web_search": true }, - "anthropic.claude-3-7-sonnet-20240620-v1:0": { - "cache_creation_input_token_cost": 0.0000045, - "cache_read_input_token_cost": 3.6e-7, - "input_cost_per_token": 0.0000036, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/doubao-seed-2-0-lite-260428": { + "cache_read_input_token_cost": 1.8082e-8, + "input_cost_per_token": 9.041e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000018, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 5.4246e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/doubao-seed-2-0-mini": { + "cache_read_input_token_cost": 6.027e-9, + "input_cost_per_token": 3.0136e-8, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 3.0136e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/doubao-seed-2-0-pro": { + "cache_read_input_token_cost": 9.644e-8, + "input_cost_per_token": 4.822e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000125, + "output_cost_per_token": 0.000002411, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 2.5e-8, - "cache_creation_input_token_cost": 3.125e-7 + "supports_web_search": true }, - "anthropic.claude-3-opus-20240229-v1:0": { - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/doubao-seed-2-1-turbo": { + "cache_read_input_token_cost": 9.295e-8, + "input_cost_per_token": 4.6475e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000075, + "output_cost_per_token": 0.00000232375, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 0.0000015, - "cache_creation_input_token_cost": 0.00001875 + "supports_web_search": true }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/ernie-5.1": { + "cache_read_input_token_cost": 5.634e-7, + "input_cost_per_token": 5.634e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 119000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.0000025353, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true + }, + "aihubmix/gemini-3-flash-preview": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 + "supports_web_search": true }, - "anthropic.claude-fable-5": { - "cache_creation_input_token_cost": 0.0000125, - "cache_creation_input_token_cost_above_1hr": 0.00002, - "cache_read_input_token_cost": 0.000001, - "input_cost_per_token": 0.00001, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "aihubmix/gemini-3-flash-preview-search": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00005, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.000003, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "supports_web_search": true }, - "anthropic.claude-fable-5-1": { - "cache_creation_input_token_cost": 0.0000125, - "cache_creation_input_token_cost_above_1hr": 0.00002, - "cache_read_input_token_cost": 2.5e-7, - "input_cost_per_token": 0.00001, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "aihubmix/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00005, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_forced_tool_use": false, + "output_cost_per_token": 0.000012, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "supports_web_search": true }, - "anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.00000125, - "cache_creation_input_token_cost_above_1hr": 0.000002, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gemini-3.1-pro-preview-customtools": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000012, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096, - "input_cost_per_token_batches": 5e-7, - "output_cost_per_token_batches": 0.0000025 + "supports_web_search": true }, - "anthropic.claude-haiku-4-5@20251001": { - "cache_creation_input_token_cost": 0.00000125, - "cache_creation_input_token_cost_above_1hr": 0.000002, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gemini-3.5-flash-lite": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 3e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000002499999, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_native_streaming": true, - "supports_native_structured_output": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "supports_web_search": true }, - "anthropic.claude-instant-v1": { - "input_cost_per_token": 8e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "aihubmix/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.0000024, - "supports_tool_choice": true + "output_cost_per_token": 0.00000375, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true }, - "anthropic.claude-mythos-preview": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "bedrock", + "aihubmix/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.4e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 3.9998e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 3.9998e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/glm-5.2-fast-preview": { + "cache_read_input_token_cost": 5.635e-7, + "input_cost_per_token": 0.000002254, + "litellm_provider": "aihubmix", "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "thinking_always_on": true, + "output_cost_per_token": 0.000007889, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_output_config": true + "supports_response_schema": true }, - "anthropic.claude-opus-4-1-20250805-v1:0": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "deprecation_date": "2027-01-08", - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "aihubmix/glm-5.3": { + "cache_read_input_token_cost": 2.817e-7, + "input_cost_per_token": 0.0000011268, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000039438, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/glm-5.3-flash": { + "cache_read_input_token_cost": 2.817e-8, + "input_cost_per_token": 1.1268e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.9438e-7, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_vision": true }, - "anthropic.claude-opus-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "bedrock_converse", + "aihubmix/glm-5v-turbo": { + "cache_read_input_token_cost": 1.69008e-7, + "input_cost_per_token": 7.042e-7, + "litellm_provider": "aihubmix", "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00000309848, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000014, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_vision": true }, - "anthropic.claude-opus-4-5-20251101-v1:0": { - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gpt-5.4-high": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000015, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "high", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "supports_web_search": true }, - "anthropic.claude-opus-4-6-v1": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, + "aihubmix/gpt-5.4-low": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.000015, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true, - "supports_output_config": true, - "supports_max_reasoning_effort": true, - "bedrock_output_config_effort_ceiling": "max", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "supports_web_search": true }, - "anthropic.claude-opus-4-7": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, + "aihubmix/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.0000045, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "supports_web_search": true }, - "anthropic.claude-opus-4-8": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "aihubmix/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.00000125, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "anthropic.claude-opus-5": { - "bedrock_converse_supports_strict_tools": false, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, + "aihubmix/gpt-5.5": { "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.00003, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "supports_web_search": true }, - "anthropic.claude-sonnet-4-20250514-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2026-10-14", - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gpt-5.5-pro": { + "input_cost_per_token": 0.00003, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00018, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, "supports_vision": true, - "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gpt-5.6-luna": { + "cache_read_input_token_cost": 2e-8, + "cache_creation_input_token_cost": 2.5e-7, + "input_cost_per_token": 2e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000012, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_native_structured_output": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024, - "input_cost_per_token_batches": 0.0000015, - "output_cost_per_token_batches": 0.0000075 + "supports_vision": true }, - "anthropic.claude-sonnet-4-6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "aihubmix/gpt-5.6-sol-disc": { + "cache_read_input_token_cost": 4e-7, + "cache_creation_input_token_cost": 0.000005, + "input_cost_per_token": 0.000004, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00002, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_native_structured_output": true, - "supports_output_config": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "supports_vision": true }, - "anthropic.claude-sonnet-5": { - "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 0.0000025, - "cache_creation_input_token_cost_above_1hr": 0.000004, + "aihubmix/gpt-5.6-terra": { "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 0.0000025, "input_cost_per_token": 0.000002, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "litellm_provider": "aihubmix", + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_adaptive_thinking": true, - "supports_mid_conversation_system": true, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 0.000012, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "aihubmix", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "source": "https://aihubmix.com/api/v1/models", "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_sampling_params": false, - "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_max_reasoning_effort": true, - "supports_output_config": true, - "bedrock_output_config_effort_ceiling": "xhigh", - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "anthropic.claude-v1": { - "input_cost_per_token": 0.000008, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "aihubmix/grok-4-20-non-reasoning": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 0.000024 + "output_cost_per_token": 0.000006, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anthropic.claude-v2:1": { - "input_cost_per_token": 0.000008, - "litellm_provider": "bedrock", - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "aihubmix/grok-4-20-reasoning": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 0.000024, - "supports_tool_choice": true + "output_cost_per_token": 0.000006, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/HuggingFaceH4/zephyr-7b-beta": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/grok-4.6": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, "mode": "chat", - "output_cost_per_token": 1.5e-7 + "output_cost_per_token": 0.000006, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "aihubmix/grok-build-0.1": { + "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000001, - "litellm_provider": "anyscale", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 0.000002, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/codellama/CodeLlama-70b-Instruct-hf": { - "input_cost_per_token": 0.000001, - "litellm_provider": "anyscale", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/hy3": { + "cache_read_input_token_cost": 3.905e-8, + "input_cost_per_token": 1.562e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000001, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" + "output_cost_per_token": 6.248e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true }, - "anyscale/google/gemma-7b-it": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/hy4-preview": { + "cache_read_input_token_cost": 4.225e-8, + "input_cost_per_token": 8.45e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" + "output_cost_per_token": 0.000002535, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true }, - "anyscale/meta-llama/Llama-2-13b-chat-hf": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/kimi-k2.6": { + "cache_read_input_token_cost": 1.60835e-7, + "input_cost_per_token": 9.5e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2.5e-7 + "output_cost_per_token": 0.0000039995, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/meta-llama/Llama-2-70b-chat-hf": { - "input_cost_per_token": 0.000001, - "litellm_provider": "anyscale", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/kimi-k2.7-code-highspeed": { + "cache_read_input_token_cost": 3.2167e-7, + "input_cost_per_token": 0.0000019, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000001 + "output_cost_per_token": 0.000007999, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/meta-llama/Llama-2-7b-chat-hf": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, + "aihubmix/kimi-k3": { + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1.5e-7 + "output_cost_per_token": 0.000015, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true }, - "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { - "input_cost_per_token": 0.000001, - "litellm_provider": "anyscale", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/longcat-2.0": { + "cache_read_input_token_cost": 1.5492e-8, + "input_cost_per_token": 7.746e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.000001, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" + "output_cost_per_token": 0.0000030984, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true }, - "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "aihubmix/mai-thinking-1": { + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" + "output_cost_per_token": 0.000008, + "source": "https://aihubmix.com/api/v1/models", + "supports_reasoning": true, + "supports_response_schema": true }, - "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/mimo-v2-omni": { + "cache_read_input_token_cost": 8.8e-8, + "input_cost_per_token": 4.4e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", - "supports_function_calling": true + "output_cost_per_token": 0.0000022, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_vision": true, + "supports_web_search": true }, - "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { - "input_cost_per_token": 9e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 65536, + "aihubmix/mimo-v2-pro": { + "cache_read_input_token_cost": 2.2e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.0000033, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_web_search": true + }, + "aihubmix/minimax-m2.7": { + "cache_read_input_token_cost": 5.916e-8, + "input_cost_per_token": 2.958e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 0.0000011832, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "aihubmix/minimax-m3": { + "input_cost_per_token": 2.88e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 0.000001152, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "aihubmix/muse-spark-1.2": { + "input_cost_per_token": 0.000001375, + "litellm_provider": "aihubmix", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.000004675, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "aihubmix/qwen3-coder-next": { + "input_cost_per_token": 1.37e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 9e-7, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", - "supports_function_calling": true + "output_cost_per_token": 5.48e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_response_schema": true }, - "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 1.5e-7, - "litellm_provider": "anyscale", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, + "aihubmix/qwen3.5-122b-a10b": { + "input_cost_per_token": 1.126e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.5e-7, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", - "supports_function_calling": true + "output_cost_per_token": 9.008e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true }, - "apac.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-8, - "input_cost_per_token": 3.3e-7, + "aihubmix/qwen3.5-397b-a17b": { + "input_cost_per_token": 1.644e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9.864e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-27b": { + "input_cost_per_token": 4.22e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000002532, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.54e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000001524, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.6-max-preview": { + "cache_read_input_token_cost": 1.268e-7, + "cache_creation_input_token_cost": 0.000001585, + "input_cost_per_token": 0.000001268, + "litellm_provider": "aihubmix", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000007608, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/qwen3.7-plus": { + "cache_read_input_token_cost": 5.64e-8, + "cache_creation_input_token_cost": 3.525e-7, + "input_cost_per_token": 2.82e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000001128, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-2.4t-a95b": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-flash": { + "cache_read_input_token_cost": 1.4075e-8, + "cache_creation_input_token_cost": 1.75937e-7, + "input_cost_per_token": 1.126e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.80025e-7, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/qwen3.8-max": { + "cache_read_input_token_cost": 1.69e-7, + "cache_creation_input_token_cost": 0.0000021125, + "input_cost_per_token": 0.00000169, + "litellm_provider": "aihubmix", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00000507, + "source": "https://aihubmix.com/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "aihubmix/step-3.7-flash": { + "cache_read_input_token_cost": 4.4e-8, + "input_cost_per_token": 2.2e-7, + "litellm_provider": "aihubmix", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.00000132, + "source": "https://aihubmix.com/api/v1/models", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "amazon-nova/nova-lite-v1": { + "input_cost_per_token": 6e-8, + "litellm_provider": "amazon_nova", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon-nova/nova-micro-v1": { + "input_cost_per_token": 3.5e-8, + "litellm_provider": "amazon_nova", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "amazon-nova/nova-premier-v1": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "amazon_nova", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon-nova/nova-pro-v1": { + "input_cost_per_token": 8e-7, + "litellm_provider": "amazon_nova", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.00000275, + "output_cost_per_token": 0.0000025, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -1040,7 +1244,7 @@ "supports_video_input": true, "supports_vision": true }, - "apac.amazon.nova-2-pro-preview-20251202-v1:0": { + "amazon.nova-2-pro-preview-20251202-v1:0": { "cache_read_input_token_cost": 5.46875e-7, "input_cost_per_token": 0.0000021875, "input_cost_per_image_token": 0.0000021875, @@ -1060,14 +1264,15 @@ "supports_video_input": true, "supports_vision": true }, - "apac.amazon.nova-lite-v1:0": { - "input_cost_per_token": 6.3e-8, + "amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 2.52e-7, + "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -1075,27 +1280,29 @@ "supports_vision": true, "supports_tool_choice": true }, - "apac.amazon.nova-micro-v1:0": { - "input_cost_per_token": 3.7e-8, + "amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 8.75e-9, + "input_cost_per_token": 3.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 1.48e-7, + "output_cost_per_token": 1.4e-7, "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, - "apac.amazon.nova-pro-v1:0": { - "input_cost_per_token": 8.4e-7, + "amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 8e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.00000336, + "output_cost_per_token": 0.0000032, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -1103,89 +1310,104 @@ "supports_vision": true, "supports_tool_choice": true }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.000003, + "amazon.titan-text-express-v1": { + "input_cost_per_token": 0.0000013, "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 + "output_cost_per_token": 0.0000017 }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.000003, + "amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-7 + }, + "amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000015 + }, + "anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.000004, "supports_assistant_prefill": true, - "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "prompt_cache_min_tokens": 2048 }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-7, + "anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000125, + "output_cost_per_token": 0.000015, "supports_function_calling": true, "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 2.5e-8, - "cache_creation_input_token_cost": 3.125e-7 + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.00003, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7 }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", + "anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.00003, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7 }, - "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, + "anthropic.claude-3-7-sonnet-20240620-v1:0": { + "cache_creation_input_token_cost": 0.0000045, + "cache_read_input_token_cost": 3.6e-7, + "input_cost_per_token": 0.0000036, + "litellm_provider": "bedrock", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000055, - "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "output_cost_per_token": 0.000018, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1194,33 +1416,18 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_native_structured_output": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096, - "input_cost_per_token_batches": 5.5e-7, - "output_cost_per_token_batches": 0.00000275 + "supports_vision": true }, - "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "anthropic.claude-3-7-sonnet-20250219-v1:0": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2026-10-14", "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -1229,51 +1436,280 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "bedrock_converse_supports_strict_tools": false, - "prompt_cache_min_tokens": 1024 + "supports_vision": true }, - "au.anthropic.claude-haiku-4-5-20251001-v1:0": { - "cache_creation_input_token_cost": 0.000001375, - "cache_creation_input_token_cost_above_1hr": 0.0000022, - "cache_read_input_token_cost": 1.1e-7, - "input_cost_per_token": 0.0000011, - "litellm_provider": "bedrock_converse", - "supports_tool_search": true, + "anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock", "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000055, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000075, "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_native_structured_output": true, - "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096, - "input_cost_per_token_batches": 5.5e-7, - "output_cost_per_token_batches": 0.00000275 + "cache_read_input_token_cost": 0.0000015, + "cache_creation_input_token_cost": 0.00001875 }, - "au.anthropic.claude-opus-4-6-v1": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_1hr": 0.000011, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000055, - "litellm_provider": "bedrock_converse", + "anthropic.claude-fable-5": { + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_1hr": 0.00002, + "cache_read_input_token_cost": 0.000001, + "input_cost_per_token": 0.00001, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00005, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "anthropic.claude-fable-5-1": { + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_1hr": 0.00002, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.00001, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00005, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5e-7, + "output_cost_per_token_batches": 0.0000025 + }, + "anthropic.claude-haiku-4-5@20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_streaming": true, + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096 + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "supports_tool_choice": true + }, + "anthropic.claude-mythos-preview": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "bedrock", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "thinking_always_on": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_output_config": true + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "deprecation_date": "2027-01-08", + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024 + }, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024 + }, + "anthropic.claude-opus-4-5-20251101-v1:0": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "high", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096 + }, + "anthropic.claude-opus-4-6-v1": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000275, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1295,20 +1731,20 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096 }, - "au.anthropic.claude-opus-4-7": { + "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_1hr": 0.000011, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000055, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000275, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1330,22 +1766,24 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "au.anthropic.claude-opus-4-8": { + "anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_1hr": 0.000011, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000055, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000275, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1367,22 +1805,24 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "au.anthropic.claude-opus-5": { + "anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_1hr": 0.000011, - "cache_read_input_token_cost": 5.5e-7, - "input_cost_per_token": 0.0000055, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000275, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1403,25 +1843,98 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 0.000004125, - "cache_creation_input_token_cost_above_1hr": 0.0000066, - "cache_read_input_token_cost": 3.3e-7, - "input_cost_per_token": 0.0000033, - "input_cost_per_token_above_200k_tokens": 0.0000066, - "output_cost_per_token_above_200k_tokens": 0.00002475, - "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00002, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2026-10-14", + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "bedrock_converse_supports_strict_tools": false, + "prompt_cache_min_tokens": 1024 + }, + "anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000165, + "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1439,23 +1952,23 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "input_cost_per_token_batches": 0.00000165, - "output_cost_per_token_batches": 0.00000825 + "input_cost_per_token_batches": 0.0000015, + "output_cost_per_token_batches": 0.0000075 }, - "au.anthropic.claude-sonnet-4-6": { + "anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.000004125, - "cache_creation_input_token_cost_above_1hr": 0.0000066, - "cache_read_input_token_cost": 3.3e-7, - "input_cost_per_token": 0.0000033, + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.0000165, + "output_cost_per_token": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1474,20 +1987,22 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "au.anthropic.claude-sonnet-5": { + "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, - "cache_creation_input_token_cost": 0.00000275, - "cache_creation_input_token_cost_above_1hr": 0.0000044, - "cache_read_input_token_cost": 2.2e-7, - "input_cost_per_token": 0.0000022, + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_1hr": 0.000004, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000011, + "output_cost_per_token": 0.00001, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -1511,639 +2026,628 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "azure/command-r-plus": { - "input_cost_per_token": 0.000003, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true + "output_cost_per_token": 0.000024 }, - "azure/computer-use-preview": { - "input_cost_per_token": 0.000003, - "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, + "anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.000012, - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure/container": { - "code_interpreter_cost_per_session": 0.03, - "litellm_provider": "azure", - "mode": "chat" + "output_cost_per_token": 0.000024, + "supports_tool_choice": true }, - "azure/eu/gpt-4o-2024-08-06": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 0.000001375, - "input_cost_per_token": 0.00000275, - "litellm_provider": "azure", - "max_input_tokens": 128000, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000011, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 1.5e-7 }, - "azure/eu/gpt-4o-2024-11-20": { - "deprecation_date": "2027-04-14", - "cache_creation_input_token_cost": 0.00000138, - "input_cost_per_token": 0.00000275, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "input_cost_per_token": 0.000001, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000011, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000001 }, - "azure/eu/gpt-4o-mini-2024-07-18": { - "cache_read_input_token_cost": 8.3e-8, - "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-7, - "litellm_provider": "azure", - "max_input_tokens": 128000, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "input_cost_per_token": 0.000001, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" + }, + "anyscale/google/gemma-7b-it": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7 + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { + "input_cost_per_token": 0.000001, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001 + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-7 + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 0.000001, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" + }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-7, + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 9e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", + "supports_function_calling": true + }, + "apac.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 8.25e-8, + "input_cost_per_token": 3.3e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.00000275, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true }, - "azure/eu/gpt-5-2025-08-07": { - "cache_read_input_token_cost": 1.375e-7, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 0.000001375, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.amazon.nova-2-pro-preview-20251202-v1:0": { + "cache_read_input_token_cost": 5.46875e-7, + "input_cost_per_token": 0.0000021875, + "input_cost_per_image_token": 0.0000021875, + "input_cost_per_audio_token": 0.0000021875, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000011, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 0.0000175, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, + "supports_video_input": true, "supports_vision": true }, - "azure/eu/gpt-5-mini-2025-08-07": { - "cache_read_input_token_cost": 2.75e-8, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 2.75e-7, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.575e-8, + "input_cost_per_token": 6.3e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.0000022, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 2.52e-7, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_tool_choice": true }, - "azure/eu/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5.5e-9, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 5.5e-8, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 9.25e-9, + "input_cost_per_token": 3.7e-8, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 4.4e-7, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 1.48e-7, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": true }, - "azure/eu/gpt-5.1": { - "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-7, - "input_cost_per_token": 0.00000138, - "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.1e-7, + "input_cost_per_token": 8.4e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, "mode": "chat", - "output_cost_per_token": 0.000011, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], + "output_cost_per_token": 0.00000336, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "supports_tool_choice": true }, - "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000138, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.000011, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-7, + "output_cost_per_token_batches": 0.00000275 }, - "azure/eu/gpt-5.4": { - "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-7, - "cache_read_input_token_cost_priority": 5.5e-7, - "input_cost_per_token": 0.00000275, - "input_cost_per_token_priority": 0.0000055, - "output_cost_per_token": 0.0000165, - "output_cost_per_token_priority": 0.000033, - "litellm_provider": "azure", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2026-10-14", + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "bedrock_converse_supports_strict_tools": false, + "prompt_cache_min_tokens": 1024 }, - "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-7, - "cache_read_input_token_cost_priority": 5.5e-7, - "deprecation_date": "2027-09-02", - "input_cost_per_token": 0.00000275, - "input_cost_per_token_priority": 0.0000055, - "output_cost_per_token": 0.0000165, - "output_cost_per_token_priority": 0.000033, - "litellm_provider": "azure", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "au.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_creation_input_token_cost_above_1hr": 0.0000022, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 0.0000055, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5.5e-7, + "output_cost_per_token_batches": 0.00000275 }, - "azure/eu/gpt-5.5": { - "deprecation_date": "2027-10-26", + "au.anthropic.claude-opus-4-6-v1": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "input_cost_per_token_priority": 0.00001375, - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, - "output_cost_per_token_priority": 0.0000825, - "litellm_provider": "azure", - "max_input_tokens": 1050000, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_max_reasoning_effort": true, + "bedrock_output_config_effort_ceiling": "max", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096 }, - "azure/eu/gpt-5.5-2026-04-23": { + "au.anthropic.claude-opus-4-7": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "input_cost_per_token_priority": 0.00001375, - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, - "output_cost_per_token_priority": 0.0000825, - "litellm_provider": "azure", - "max_input_tokens": 1050000, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "deprecation_date": "2027-10-26" + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 2048 }, - "azure/eu/gpt-5.6": { + "au.anthropic.claude-opus-4-8": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, - "cache_creation_input_token_cost_priority": 0.00001375, + "cache_creation_input_token_cost_above_1hr": 0.000011, "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, - "cache_read_input_token_cost_priority": 0.0000011, "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "input_cost_per_token_above_272k_tokens_priority": 0.000022, - "input_cost_per_token_priority": 0.000011, - "litellm_provider": "azure", - "max_input_tokens": 922000, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, - "output_cost_per_token_above_272k_tokens_priority": 0.000099, - "output_cost_per_token_priority": 0.000066, + "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024 }, - "azure/eu/gpt-5.6-luna": { - "cache_creation_input_token_cost": 2.75e-7, - "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, - "cache_creation_input_token_cost_priority": 5.5e-7, - "cache_read_input_token_cost": 2.2e-8, - "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, - "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, - "cache_read_input_token_cost_priority": 4.4e-8, - "deprecation_date": "2028-01-11", - "input_cost_per_token": 2.2e-7, - "input_cost_per_token_above_272k_tokens": 4.4e-7, - "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, - "input_cost_per_token_priority": 4.4e-7, - "litellm_provider": "azure", - "max_input_tokens": 922000, + "au.anthropic.claude-opus-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_1hr": 0.000011, + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000055, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000132, - "output_cost_per_token_above_272k_tokens": 0.00000198, - "output_cost_per_token_above_272k_tokens_priority": 0.00000396, - "output_cost_per_token_priority": 0.00000264, + "output_cost_per_token": 0.0000275, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512 }, - "azure/eu/gpt-5.6-sol": { - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, - "cache_creation_input_token_cost_priority": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, - "cache_read_input_token_cost_priority": 0.0000011, - "deprecation_date": "2028-01-11", - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "input_cost_per_token_above_272k_tokens_priority": 0.000022, - "input_cost_per_token_priority": 0.000011, - "litellm_provider": "azure", - "max_input_tokens": 922000, + "au.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_1hr": 0.0000088, + "cache_read_input_token_cost": 2.2e-7, + "input_cost_per_token": 0.0000044, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, - "output_cost_per_token_above_272k_tokens_priority": 0.000099, - "output_cost_per_token_priority": 0.000066, + "output_cost_per_token": 0.000022, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "supports_assistant_prefill": false, + "supports_computer_use": true, "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" }, - "azure/eu/gpt-5.6-terra": { + "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_creation_input_token_cost_above_1hr": 0.0000066, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024, + "input_cost_per_token_batches": 0.00000165, + "output_cost_per_token_batches": 0.00000825 + }, + "au.anthropic.claude-sonnet-4-6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 0.000004125, + "cache_creation_input_token_cost_above_1hr": 0.0000066, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024 + }, + "au.anthropic.claude-sonnet-5": { + "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 0.00000275, - "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, - "cache_creation_input_token_cost_priority": 0.0000055, + "cache_creation_input_token_cost_above_1hr": 0.0000044, "cache_read_input_token_cost": 2.2e-7, - "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, - "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, - "cache_read_input_token_cost_priority": 4.4e-7, - "deprecation_date": "2028-01-11", "input_cost_per_token": 0.0000022, - "input_cost_per_token_above_272k_tokens": 0.0000044, - "input_cost_per_token_above_272k_tokens_priority": 0.0000088, - "input_cost_per_token_priority": 0.0000044, - "litellm_provider": "azure", - "max_input_tokens": 922000, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000132, - "output_cost_per_token_above_272k_tokens": 0.0000198, - "output_cost_per_token_above_272k_tokens_priority": 0.0000396, - "output_cost_per_token_priority": 0.0000264, + "output_cost_per_token": 0.000011, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 1024 + }, + "azure/chat-latest": { + "cache_read_input_token_cost": 5e-7, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 0.000005, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -2163,149 +2667,168 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_web_search": true }, - "azure/eu/o1-2024-12-17": { - "cache_read_input_token_cost": 0.00000825, - "deprecation_date": "2026-10-21", - "input_cost_per_token": 0.0000165, + "azure/command-r-plus": { + "input_cost_per_token": 0.000003, "litellm_provider": "azure", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000066, + "output_cost_per_token": 0.000015, + "supports_function_calling": true + }, + "azure/computer-use-preview": { + "input_cost_per_token": 0.000003, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000012, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/eu/o1-mini-2024-09-12": { - "cache_read_input_token_cost": 6.05e-7, - "input_cost_per_token": 0.00000121, - "input_cost_per_token_batches": 6.05e-7, + "azure/container": { + "code_interpreter_cost_per_session": 0.03, + "litellm_provider": "azure", + "mode": "chat" + }, + "azure/eu/codex-mini": { + "deprecation_date": "2026-11-15", + "cache_read_input_token_cost": 4.13e-7, + "input_cost_per_token": 0.00000165, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00000484, - "output_cost_per_token_batches": 0.00000242, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_vision": false + "output_cost_per_token": 0.0000066, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 0.00000825, - "input_cost_per_token": 0.0000165, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 0.0000033, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000066, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_vision": false + "output_cost_per_token": 0.0000132, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/eu/o3-mini-2025-01-31": { - "cache_read_input_token_cost": 6.05e-7, - "deprecation_date": "2026-10-01", - "input_cost_per_token": 0.00000121, - "input_cost_per_token_batches": 6.05e-7, + "azure/eu/gpt-4.1": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_priority": 9.63e-7, + "input_cost_per_token": 0.0000022, + "input_cost_per_token_batches": 0.0000011, + "input_cost_per_token_priority": 0.00000385, "litellm_provider": "azure", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.00000484, - "output_cost_per_token_batches": 0.00000242, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false + "output_cost_per_token": 0.0000088, + "output_cost_per_token_batches": 0.0000044, + "output_cost_per_token_priority": 0.0000154, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/global-standard/gpt-4o-2024-08-06": { - "cache_read_input_token_cost": 0.00000125, + "azure/eu/gpt-4.1-mini": { "deprecation_date": "2027-04-14", - "input_cost_per_token": 0.0000025, + "cache_read_input_token_cost": 1.1e-7, + "cache_read_input_token_cost_priority": 1.93e-7, + "input_cost_per_token": 4.4e-7, + "input_cost_per_token_batches": 2.2e-7, + "input_cost_per_token_priority": 7.7e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.00000176, + "output_cost_per_token_batches": 8.8e-7, + "output_cost_per_token_priority": 0.00000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/global-standard/gpt-4o-2024-11-20": { - "cache_read_input_token_cost": 0.00000125, + "azure/eu/gpt-4.1-nano": { "deprecation_date": "2027-04-14", - "input_cost_per_token": 0.0000025, + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 1.1e-7, + "input_cost_per_token_batches": 5.5e-8, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/global-standard/gpt-4o-mini": { + "azure/eu/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", + "input_cost_per_token": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000165, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.5e-7, + "cache_read_input_token_cost": 0.000001375, + "input_cost_per_token": 0.00000275, + "input_cost_per_token_batches": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/global/gpt-4o-2024-08-06": { + "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, + "cache_creation_input_token_cost": 0.00000138, + "cache_read_input_token_cost": 0.000001375, + "input_cost_per_token": 0.00000275, + "input_cost_per_token_batches": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/global/gpt-4o-2024-11-20": { + "azure/eu/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-8, "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, + "input_cost_per_token": 1.65e-7, + "input_cost_per_token_batches": 8.3e-8, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 6.6e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -2313,16 +2836,37 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/global/gpt-5.1": { - "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "azure/eu/gpt-5": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_batches": 6.875e-8, + "cache_read_input_token_cost_priority": 2.75e-7, + "input_cost_per_token": 0.000001375, + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_priority": 2.75e-7, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 0.000001375, + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2333,8 +2877,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -2346,19 +2889,48 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "cache_read_input_token_cost_batches": 6.875e-8 }, - "azure/global/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000125, + "azure/eu/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "cache_read_input_token_cost": 1.38e-7, + "input_cost_per_token": 0.000001375, "litellm_provider": "azure", - "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 2.75e-8, + "cache_read_input_token_cost_batches": 1.375e-8, + "cache_read_input_token_cost_priority": 4.95e-8, + "input_cost_per_token": 2.75e-7, + "input_cost_per_token_batches": 1.375e-7, + "input_cost_per_token_priority": 4.95e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000022, + "output_cost_per_token_batches": 0.0000011, + "output_cost_per_token_priority": 0.00000396, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.75e-8, + "cache_read_input_token_cost_priority": 4.95e-8, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 2.75e-7, + "input_cost_per_token_batches": 1.375e-7, + "input_cost_per_token_priority": 4.95e-7, + "litellm_provider": "azure", + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.0000022, + "output_cost_per_token_batches": 0.0000011, + "output_cost_per_token_priority": 0.00000396, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2369,8 +2941,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -2382,205 +2953,333 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "cache_read_input_token_cost_batches": 1.375e-8 }, - "azure/gpt-3.5-turbo": { - "input_cost_per_token": 5e-7, + "azure/eu/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 5.5e-9, + "cache_read_input_token_cost_batches": 2.75e-9, + "input_cost_per_token": 5.5e-8, + "input_cost_per_token_batches": 2.75e-8, "litellm_provider": "azure", - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-3.5-turbo-0125": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 5e-7, - "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, + "azure/eu/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5.5e-9, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 5.5e-8, + "input_cost_per_token_batches": 2.75e-8, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000015, + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-9 }, - "azure/gpt-35-turbo": { - "input_cost_per_token": 5e-7, + "azure/eu/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "input_cost_per_token": 0.0000165, + "input_cost_per_token_batches": 0.00000825, "litellm_provider": "azure", - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 0.000066, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-35-turbo-0125": { - "deprecation_date": "2025-05-31", - "input_cost_per_token": 5e-7, + "azure/eu/gpt-5.1": { + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_batches": 6.875e-8, + "cache_read_input_token_cost_priority": 2.75e-7, + "input_cost_per_token": 0.000001375, "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "deprecation_date": "2025-03-31", - "input_cost_per_token": 0.000001, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "cache_read_input_token_cost": 1.375e-7, + "input_cost_per_token": 0.000001375, "litellm_provider": "azure", - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.000011, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-35-turbo-16k": { - "input_cost_per_token": 0.000003, + "azure/eu/gpt-5.2": { + "deprecation_date": "2027-06-08", + "cache_read_input_token_cost": 1.925e-7, + "cache_read_input_token_cost_batches": 9.625e-8, + "cache_read_input_token_cost_priority": 3.85e-7, + "input_cost_per_token": 0.000001925, + "input_cost_per_token_batches": 9.625e-7, + "input_cost_per_token_priority": 0.00000385, "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_tool_choice": true + "output_cost_per_token": 0.0000154, + "output_cost_per_token_batches": 0.0000077, + "output_cost_per_token_priority": 0.0000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-35-turbo-16k-0613": { - "input_cost_per_token": 0.000003, + "azure/eu/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "cache_read_input_token_cost": 1.925e-7, + "input_cost_per_token": 0.000001925, "litellm_provider": "azure", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000004, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000154, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4": { - "input_cost_per_token": 0.00003, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 0.0000231, + "input_cost_per_token_batches": 0.00001155, "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 0.0000924, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4-0125-preview": { - "input_cost_per_token": 0.00001, + "azure/eu/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "cache_read_input_token_cost": 1.925e-7, + "cache_read_input_token_cost_priority": 3.85e-7, + "input_cost_per_token": 0.000001925, + "input_cost_per_token_priority": 0.00000385, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000154, + "output_cost_per_token_priority": 0.0000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4-0613": { - "input_cost_per_token": 0.00003, + "azure/eu/gpt-5.4": { + "deprecation_date": "2027-09-02", + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-7, + "cache_read_input_token_cost_batches": 1.43e-7, + "cache_read_input_token_cost_priority": 5.5e-7, + "input_cost_per_token": 0.00000275, + "input_cost_per_token_priority": 0.0000055, + "output_cost_per_token": 0.0000165, + "output_cost_per_token_priority": 0.000033, "litellm_provider": "azure", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00006, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_tool_choice": true + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 0.0000055, + "input_cost_per_token_above_272k_tokens_batches": 0.00000275, + "input_cost_per_token_batches": 0.000001375, + "output_cost_per_token_above_272k_tokens": 0.00002475, + "output_cost_per_token_above_272k_tokens_batches": 0.000012375, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true }, - "azure/gpt-4-1106-preview": { - "input_cost_per_token": 0.00001, + "azure/eu/gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, + "cache_read_input_token_cost_priority": 5.5e-7, + "deprecation_date": "2027-09-02", + "input_cost_per_token": 0.00000275, + "input_cost_per_token_priority": 0.0000055, + "output_cost_per_token": 0.0000165, + "output_cost_per_token_priority": 0.000033, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00003, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-4-32k": { - "input_cost_per_token": 0.00006, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "supports_tool_choice": true - }, - "azure/gpt-4-32k-0613": { - "input_cost_per_token": 0.00006, - "litellm_provider": "azure", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00012, - "supports_tool_choice": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 0.0000055, + "input_cost_per_token_batches": 0.000001375, + "output_cost_per_token_above_272k_tokens": 0.00002475, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-7, + "cache_read_input_token_cost_batches": 1.43e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.00000275, + "output_cost_per_token_above_272k_tokens_batches": 0.000012375 }, - "azure/gpt-4-turbo": { - "input_cost_per_token": 0.00001, + "azure/eu/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 8.25e-8, + "cache_read_input_token_cost_batches": 4.125e-8, + "cache_read_input_token_cost_priority": 1.65e-7, + "input_cost_per_token": 8.25e-7, + "input_cost_per_token_batches": 4.125e-7, + "input_cost_per_token_priority": 0.00000165, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 0.00000495, + "output_cost_per_token_batches": 0.000002475, + "output_cost_per_token_priority": 0.0000099, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 0.00001, + "azure/eu/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 2.2e-8, + "cache_read_input_token_cost_batches": 1.1e-8, + "input_cost_per_token": 2.2e-7, + "input_cost_per_token_batches": 1.1e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000001375, + "output_cost_per_token_batches": 6.875e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4-turbo-vision-preview": { - "input_cost_per_token": 0.00001, + "azure/eu/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "input_cost_per_token": 0.000033, + "input_cost_per_token_above_272k_tokens": 0.000066, + "input_cost_per_token_above_272k_tokens_batches": 0.000033, + "input_cost_per_token_batches": 0.0000165, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 0.000099, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4.1": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, + "azure/eu/gpt-5.5": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.0000011, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "cache_read_input_token_cost_priority": 0.000001375, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_272k_tokens": 0.000011, + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "input_cost_per_token_priority": 0.00001375, + "output_cost_per_token": 0.000033, + "output_cost_per_token_above_272k_tokens": 0.0000495, + "output_cost_per_token_priority": 0.0000825, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, + "output_cost_per_token_above_272k_tokens_batches": 0.00002475, + "output_cost_per_token_batches": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2596,25 +3295,40 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, - "azure/gpt-4.1-2025-04-14": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, + "azure/eu/gpt-5.5-2026-04-23": { + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.0000011, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "cache_read_input_token_cost_priority": 0.000001375, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_272k_tokens": 0.000011, + "input_cost_per_token_priority": 0.00001375, + "output_cost_per_token": 0.000033, + "output_cost_per_token_above_272k_tokens": 0.0000495, + "output_cost_per_token_priority": 0.0000825, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2630,25 +3344,44 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "output_cost_per_token_above_272k_tokens_batches": 0.00002475, + "output_cost_per_token_batches": 0.0000165, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-4.1-mini": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, - "input_cost_per_token_batches": 2e-7, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.0000011, + "cache_read_input_token_cost_priority": 0.000001375, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "input_cost_per_token_above_272k_tokens": 0.000011, + "input_cost_per_token_priority": 0.00001375, + "output_cost_per_token": 0.000033, + "output_cost_per_token_batches": 0.0000165, + "output_cost_per_token_above_272k_tokens": 0.0000495, + "output_cost_per_token_priority": 0.0000825, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000016, - "output_cost_per_token_batches": 8e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2664,25 +3397,50 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "output_cost_per_token_above_272k_tokens_batches": 0.00002475 }, - "azure/gpt-4.1-mini-2025-04-14": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, - "input_cost_per_token_batches": 2e-7, + "azure/eu/gpt-5.6": { + "cache_creation_input_token_cost": 0.000006875, + "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, + "cache_creation_input_token_cost_priority": 0.00001375, + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.0000011, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, + "cache_read_input_token_cost_priority": 0.0000011, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_272k_tokens": 0.000011, + "input_cost_per_token_above_272k_tokens_priority": 0.000022, + "input_cost_per_token_priority": 0.000011, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000016, - "output_cost_per_token_batches": 8e-7, + "output_cost_per_token": 0.000033, + "output_cost_per_token_above_272k_tokens": 0.0000495, + "output_cost_per_token_above_272k_tokens_priority": 0.000099, + "output_cost_per_token_priority": 0.000066, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2698,25 +3456,47 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": false + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, - "azure/gpt-4.1-nano": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 1e-7, - "input_cost_per_token_batches": 5e-8, + "azure/eu/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-7, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, + "cache_creation_input_token_cost_priority": 5.5e-7, + "cache_read_input_token_cost": 2.2e-8, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, + "cache_read_input_token_cost_priority": 4.4e-8, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2.2e-7, + "input_cost_per_token_above_272k_tokens": 4.4e-7, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, + "input_cost_per_token_priority": 4.4e-7, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, - "output_cost_per_token_batches": 2e-7, + "output_cost_per_token": 0.00000132, + "output_cost_per_token_above_272k_tokens": 0.00000198, + "output_cost_per_token_above_272k_tokens_priority": 0.00000396, + "output_cost_per_token_priority": 0.00000264, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2732,24 +3512,47 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, - "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 1e-7, - "input_cost_per_token_batches": 5e-8, + "azure/eu/gpt-5.6-sol": { + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_272k_tokens": 0.000011, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, + "cache_creation_input_token_cost_priority": 0.000011, + "cache_read_input_token_cost": 4.4e-7, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, + "cache_read_input_token_cost_priority": 8.8e-7, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 0.0000044, + "input_cost_per_token_above_272k_tokens": 0.0000088, + "input_cost_per_token_above_272k_tokens_priority": 0.0000176, + "input_cost_per_token_priority": 0.0000088, "litellm_provider": "azure", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, - "output_cost_per_token_batches": 2e-7, + "output_cost_per_token": 0.000022, + "output_cost_per_token_above_272k_tokens": 0.000033, + "output_cost_per_token_above_272k_tokens_priority": 0.000066, + "output_cost_per_token_priority": 0.000044, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -2765,89 +3568,195 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, - "azure/gpt-4.5-preview": { - "cache_read_input_token_cost": 0.0000375, - "input_cost_per_token": 0.000075, - "input_cost_per_token_batches": 0.0000375, + "azure/eu/gpt-5.6-terra": { + "cache_creation_input_token_cost": 0.00000275, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, + "cache_creation_input_token_cost_priority": 0.0000055, + "cache_read_input_token_cost": 2.2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, + "cache_read_input_token_cost_priority": 4.4e-7, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 0.0000022, + "input_cost_per_token_above_272k_tokens": 0.0000044, + "input_cost_per_token_above_272k_tokens_priority": 0.0000088, + "input_cost_per_token_priority": 0.0000044, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_batches": 0.000075, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000132, + "output_cost_per_token_above_272k_tokens": 0.0000198, + "output_cost_per_token_above_272k_tokens_priority": 0.0000396, + "output_cost_per_token_priority": 0.0000264, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, - "azure/gpt-4o": { - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, + "azure/eu/gpt-6-astra": { + "cache_creation_input_token_cost": 0.00001375, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, + "cache_read_input_token_cost": 0.0000011, + "cache_read_input_token_cost_above_272k_tokens": 0.0000022, + "input_cost_per_token": 0.000011, + "input_cost_per_token_above_272k_tokens": 0.000022, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000055, + "output_cost_per_token_above_272k_tokens": 0.0000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-2024-12-17": { + "cache_read_input_token_cost": 0.00000825, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 0.0000165, + "input_cost_per_token_batches": 0.00000825, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000066, + "output_cost_per_token_batches": 0.000033, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4o-2024-05-13": { - "deprecation_date": "2026-10-01", - "input_cost_per_token": 0.000005, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "azure/gpt-4o-2024-08-06": { - "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.0000025, + "azure/eu/o3-2025-04-16": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000022, + "input_cost_per_token_batches": 0.0000011, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 0.0000088, + "output_cost_per_token_batches": 0.0000044, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000044, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-7, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, - "azure/gpt-4o-2024-11-20": { - "deprecation_date": "2027-04-14", + "azure/eu/o4-mini-2025-04-16": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 3.03e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/global-standard/gpt-4o-2024-08-06": { "cache_read_input_token_cost": 0.00000125, - "input_cost_per_token": 0.00000275, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000011, + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -2855,64 +3764,53 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4o-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 0.00004, + "azure/global-standard/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 0.00000125, + "deprecation_date": "2027-04-14", "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "azure/gpt-4o-mini": { + "azure/global-standard/gpt-4o-mini": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 7.5e-8, - "input_cost_per_token": 1.65e-7, + "input_cost_per_token": 1.5e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-7, + "output_cost_per_token": 6e-7, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4o-mini-2024-07-18": { - "cache_read_input_token_cost": 7.5e-8, + "azure/global/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-7, + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -2920,40 +3818,31 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 0.00004, + "azure/global/gpt-4o-2024-11-20": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.00008, "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, - "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, - "azure/gpt-5": { - "deprecation_date": "2027-02-09", + "azure/global/gpt-5.1": { + "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -2971,7 +3860,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -2982,18 +3872,176 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.00002, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo": { + "input_cost_per_token": 5e-7, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k": { + "input_cost_per_token": 0.000003, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k-0613": { + "input_cost_per_token": 0.000003, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4": { + "input_cost_per_token": 0.00003, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-0125-preview": { + "input_cost_per_token": 0.00001, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-0613": { + "input_cost_per_token": 0.00003, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-1106-preview": { + "input_cost_per_token": 0.00001, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-32k": { + "input_cost_per_token": 0.00006, + "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true + }, + "azure/gpt-4-32k-0613": { + "input_cost_per_token": 0.00006, + "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true + }, + "azure/gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 0.00001, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-2025-08-07": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 0.00000125, + "azure/gpt-4-turbo-vision-preview": { + "input_cost_per_token": 0.00001, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4.1": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000035, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "output_cost_per_token_priority": 0.000014, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3009,25 +4057,29 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "azure/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000125, + "azure/gpt-4.1-2025-04-14": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00001, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "output_cost_per_token_priority": 0.000014, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3043,24 +4095,29 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "azure/gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000125, + "azure/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_priority": 1.75e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "input_cost_per_token_priority": 7e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "output_cost_per_token_priority": 0.0000028, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3076,24 +4133,29 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "azure/gpt-5-mini": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 2.5e-7, + "azure/gpt-4.1-mini-2025-04-14": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_priority": 1.75e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "input_cost_per_token_priority": 7e-7, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "output_cost_per_token_priority": 0.0000028, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3109,24 +4171,26 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "azure/gpt-5-mini-2025-08-07": { + "azure/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 2.5e-7, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3142,24 +4206,25 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-nano": { - "deprecation_date": "2027-02-09", - "cache_read_input_token_cost": 5e-9, - "input_cost_per_token": 5e-8, + "azure/gpt-4.1-nano-2025-04-14": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, "litellm_provider": "azure", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3175,24 +4240,222 @@ "supports_function_calling": true, "supports_native_streaming": true, "supports_parallel_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5-nano-2025-08-07": { - "cache_read_input_token_cost": 5e-9, - "deprecation_date": "2027-02-09", - "input_cost_per_token": 5e-8, - "litellm_provider": "azure", - "max_input_tokens": 272000, + "azure/gpt-4.5-preview": { + "cache_read_input_token_cost": 0.0000375, + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", + "input_cost_per_token": 0.000005, + "input_cost_per_token_batches": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-08-06": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-11-20": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-4o-mini": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.65e-7, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-8, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-5": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.00002, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3216,16 +4479,22 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.1": { - "deprecation_date": "2027-05-15", + "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "deprecation_date": "2027-02-09", "input_cost_per_token": 0.00000125, + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.00002, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3236,8 +4505,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3249,24 +4517,28 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "cache_read_input_token_cost_batches": 6.25e-8 }, - "azure/gpt-5.1-2025-11-13": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, - "deprecation_date": "2027-05-15", - "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, + "azure/gpt-5-mini": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_batches": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, + "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -3274,8 +4546,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3286,21 +4557,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_minimal_reasoning_effort": true + "supports_vision": true }, - "azure/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000125, + "azure/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_batches": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3311,8 +4585,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3324,24 +4597,25 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "cache_read_input_token_cost_batches": 1.25e-8 }, - "azure/gpt-5.1-chat-2025-11-13": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, + "azure/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_batches": 2.5e-9, + "input_cost_per_token": 5e-8, + "input_cost_per_token_batches": 2.5e-8, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -3349,32 +4623,32 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], - "supports_function_calling": false, + "supports_function_calling": true, "supports_native_streaming": true, - "supports_parallel_function_calling": false, + "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-5.2": { - "deprecation_date": "2027-06-08", - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, + "azure/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-9, + "deprecation_date": "2027-02-09", + "input_cost_per_token": 5e-8, + "input_cost_per_token_batches": 2.5e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000014, + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3385,8 +4659,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3397,21 +4670,21 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-9 }, - "azure/gpt-5.2-2025-12-11": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2027-06-08", - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, + "azure/gpt-5.1": { + "deprecation_date": "2027-05-15", + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, + "output_cost_per_token": 0.00001, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3434,21 +4707,28 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.00002, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/gpt-5.2-chat": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, + "azure/gpt-5.1-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "deprecation_date": "2027-05-15", + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -3458,7 +4738,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3469,23 +4750,35 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-7, + "output_cost_per_token_batches": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-8 }, - "azure/gpt-5.2-chat-2025-12-11": { + "azure/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_batches": 8.75e-8, "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2026-05-13", "input_cost_per_token": 0.00000175, + "input_cost_per_token_batches": 8.75e-7, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, + "output_cost_per_token_batches": 0.000007, "output_cost_per_token_priority": 0.000028, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -3493,7 +4786,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3506,21 +4800,25 @@ "supports_tool_choice": true, "supports_vision": true }, - "azure/gpt-5.3-chat": { + "azure/gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-7, "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2026-06-29", + "deprecation_date": "2027-06-08", "input_cost_per_token": 0.00000175, + "input_cost_per_token_batches": 8.75e-7, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000014, + "output_cost_per_token_batches": 0.000007, "output_cost_per_token_priority": 0.000028, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -3528,7 +4826,8 @@ "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -3539,14 +4838,18 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-8 }, "azure/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, + "cache_read_input_token_cost_batches": 1.3e-7, "input_cost_per_token": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, @@ -3584,12 +4887,22 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_batches": 0.0000025, + "input_cost_per_token_above_272k_tokens_flex": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_flex": 0.00000125, + "output_cost_per_token_above_272k_tokens_batches": 0.00001125, + "output_cost_per_token_above_272k_tokens_flex": 0.00001125, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_flex": 0.0000075, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "deprecation_date": "2027-09-02", @@ -3630,12 +4943,26 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_flex": 0.00000125, + "output_cost_per_token_above_272k_tokens_flex": 0.00001125, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_flex": 0.0000075, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-7, + "cache_read_input_token_cost_batches": 1.3e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.0000025, + "output_cost_per_token_above_272k_tokens_batches": 0.00001125 }, "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, + "cache_read_input_token_cost_flex": 3.75e-8, + "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -3673,10 +5000,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-7, + "input_cost_per_token_flex": 3.75e-7, + "input_cost_per_token_priority": 0.0000015, + "output_cost_per_token_batches": 0.00000225, + "output_cost_per_token_flex": 0.00000225, + "output_cost_per_token_priority": 0.000009, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_flex": 3.75e-8, + "cache_read_input_token_cost_priority": 1.5e-7, "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-7, "litellm_provider": "azure", @@ -3715,11 +5051,21 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true + "input_cost_per_token_batches": 3.75e-7, + "input_cost_per_token_flex": 3.75e-7, + "input_cost_per_token_priority": 0.0000015, + "output_cost_per_token_batches": 0.00000225, + "output_cost_per_token_flex": 0.00000225, + "output_cost_per_token_priority": 0.000009, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-8 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_batches": 1e-8, + "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token": 2e-7, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -3757,10 +5103,16 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-7, + "input_cost_per_token_flex": 1e-7, + "output_cost_per_token_batches": 6.25e-7, + "output_cost_per_token_flex": 6.25e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_flex": 1e-8, "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-7, "litellm_provider": "azure", @@ -3799,18 +5151,31 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true + "input_cost_per_token_batches": 1e-7, + "input_cost_per_token_flex": 1e-7, + "output_cost_per_token_batches": 6.25e-7, + "output_cost_per_token_flex": 6.25e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-8 }, "azure/gpt-5.5": { "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, - "cache_read_input_token_cost_priority": 0.000001, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, + "cache_read_input_token_cost_priority": 0.00000125, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, + "cache_read_input_token_cost_batches": 2.5e-7, + "cache_read_input_token_cost_flex": 2.5e-7, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, - "input_cost_per_token_priority": 0.00001, + "input_cost_per_token_above_272k_tokens_batches": 0.000005, + "input_cost_per_token_above_272k_tokens_flex": 0.000005, + "input_cost_per_token_priority": 0.0000125, "input_cost_per_token_above_272k_tokens_priority": 0.00002, + "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_flex": 0.0000025, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -3818,13 +5183,16 @@ "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, - "output_cost_per_token_priority": 0.00006, + "output_cost_per_token_above_272k_tokens_batches": 0.0000225, + "output_cost_per_token_priority": 0.000075, "output_cost_per_token_above_272k_tokens_priority": 0.00009, + "output_cost_per_token_batches": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -3855,11 +5223,14 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, - "cache_read_input_token_cost_priority": 0.000001, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, + "cache_read_input_token_cost_priority": 0.00000125, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, + "cache_read_input_token_cost_batches": 2.5e-7, + "cache_read_input_token_cost_flex": 2.5e-7, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, - "input_cost_per_token_priority": 0.00001, + "input_cost_per_token_priority": 0.0000125, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "litellm_provider": "azure", "max_input_tokens": 1050000, @@ -3868,7 +5239,68 @@ "mode": "chat", "output_cost_per_token": 0.00003, "output_cost_per_token_above_272k_tokens": 0.000045, - "output_cost_per_token_priority": 0.00006, + "output_cost_per_token_priority": 0.000075, + "output_cost_per_token_above_272k_tokens_priority": 0.00009, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 0.000005, + "input_cost_per_token_above_272k_tokens_flex": 0.000005, + "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_flex": 0.0000025, + "output_cost_per_token_above_272k_tokens_batches": 0.0000225, + "output_cost_per_token_batches": 0.000015, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "cache_read_input_token_cost_priority": 0.00000125, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, + "cache_read_input_token_cost_flex": 2.5e-7, + "input_cost_per_token": 0.000005, + "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_above_272k_tokens": 0.00001, + "input_cost_per_token_above_272k_tokens_flex": 0.000005, + "input_cost_per_token_priority": 0.0000125, + "input_cost_per_token_above_272k_tokens_priority": 0.00002, + "input_cost_per_token_flex": 0.0000025, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "output_cost_per_token_batches": 0.000015, + "output_cost_per_token_above_272k_tokens": 0.000045, + "output_cost_per_token_priority": 0.000075, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -3898,7 +5330,14 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, + "cache_read_input_token_cost_batches": 2.5e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.000005, + "output_cost_per_token_above_272k_tokens_batches": 0.0000225 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 0.00000625, @@ -3957,17 +5396,23 @@ "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-7, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, + "cache_creation_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost": 2e-8, "cache_read_input_token_cost_above_272k_tokens": 4e-8, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, + "cache_read_input_token_cost_flex": 1e-8, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-7, "input_cost_per_token_above_272k_tokens": 4e-7, + "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, + "input_cost_per_token_flex": 1e-7, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -3975,13 +5420,16 @@ "mode": "chat", "output_cost_per_token": 0.0000012, "output_cost_per_token_above_272k_tokens": 0.0000018, + "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_priority": 0.0000024, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, + "output_cost_per_token_flex": 6e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4009,34 +5457,171 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, - "azure/gpt-5.6-sol": { - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, - "cache_creation_input_token_cost_priority": 0.0000125, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000025, - "cache_read_input_token_cost": 5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.000001, - "cache_read_input_token_cost_priority": 0.000001, - "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-7, + "cache_creation_input_token_cost_above_272k_tokens": 5e-7, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, + "cache_creation_input_token_cost_priority": 5e-7, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, + "cache_creation_input_token_cost_flex": 1.25e-7, + "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_above_272k_tokens": 4e-8, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, + "cache_read_input_token_cost_priority": 4e-8, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, + "cache_read_input_token_cost_flex": 1e-8, "deprecation_date": "2028-01-11", - "input_cost_per_token": 0.000005, - "input_cost_per_token_above_272k_tokens": 0.00001, - "input_cost_per_token_priority": 0.00001, - "input_cost_per_token_above_272k_tokens_priority": 0.00002, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_272k_tokens": 4e-7, + "input_cost_per_token_above_272k_tokens_flex": 2e-7, + "input_cost_per_token_priority": 4e-7, + "input_cost_per_token_above_272k_tokens_priority": 8e-7, + "input_cost_per_token_flex": 1e-7, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00003, - "output_cost_per_token_above_272k_tokens": 0.000045, - "output_cost_per_token_priority": 0.00006, - "output_cost_per_token_above_272k_tokens_priority": 0.00009, + "output_cost_per_token": 0.0000012, + "output_cost_per_token_above_272k_tokens": 0.0000018, + "output_cost_per_token_above_272k_tokens_flex": 9e-7, + "output_cost_per_token_priority": 0.0000024, + "output_cost_per_token_above_272k_tokens_priority": 0.0000036, + "output_cost_per_token_flex": 6e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/gpt-5.6-sol": { + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens": 0.00001, + "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, + "cache_creation_input_token_cost_priority": 0.00001, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, + "cache_creation_input_token_cost_flex": 0.0000025, + "cache_read_input_token_cost": 4e-7, + "cache_read_input_token_cost_above_272k_tokens": 8e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, + "cache_read_input_token_cost_priority": 8e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, + "cache_read_input_token_cost_flex": 2e-7, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 0.000004, + "input_cost_per_token_above_272k_tokens": 0.000008, + "input_cost_per_token_above_272k_tokens_flex": 0.000004, + "input_cost_per_token_priority": 0.000008, + "input_cost_per_token_above_272k_tokens_priority": 0.000016, + "input_cost_per_token_flex": 0.000002, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00002, + "output_cost_per_token_above_272k_tokens": 0.00003, + "output_cost_per_token_above_272k_tokens_flex": 0.000015, + "output_cost_per_token_priority": 0.00004, + "output_cost_per_token_above_272k_tokens_priority": 0.00006, + "output_cost_per_token_flex": 0.00001, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens": 0.00001, + "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, + "cache_creation_input_token_cost_priority": 0.00001, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, + "cache_creation_input_token_cost_flex": 0.0000025, + "cache_read_input_token_cost": 4e-7, + "cache_read_input_token_cost_above_272k_tokens": 8e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, + "cache_read_input_token_cost_priority": 8e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, + "cache_read_input_token_cost_flex": 2e-7, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 0.000004, + "input_cost_per_token_above_272k_tokens": 0.000008, + "input_cost_per_token_above_272k_tokens_flex": 0.000004, + "input_cost_per_token_priority": 0.000008, + "input_cost_per_token_above_272k_tokens_priority": 0.000016, + "input_cost_per_token_flex": 0.000002, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00002, + "output_cost_per_token_above_272k_tokens": 0.00003, + "output_cost_per_token_above_272k_tokens_flex": 0.000015, + "output_cost_per_token_priority": 0.00004, + "output_cost_per_token_above_272k_tokens_priority": 0.00006, + "output_cost_per_token_flex": 0.00001, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4067,17 +5652,23 @@ "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, + "cache_creation_input_token_cost_flex": 0.00000125, "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_priority": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, + "cache_read_input_token_cost_flex": 1e-7, "deprecation_date": "2028-01-11", "input_cost_per_token": 0.000002, "input_cost_per_token_above_272k_tokens": 0.000004, + "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_priority": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, + "input_cost_per_token_flex": 0.000001, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -4085,13 +5676,80 @@ "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_above_272k_tokens": 0.000018, + "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_priority": 0.000024, "output_cost_per_token_above_272k_tokens_priority": 0.000036, + "output_cost_per_token_flex": 0.000006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, + "cache_creation_input_token_cost_priority": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, + "cache_creation_input_token_cost_flex": 0.00000125, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, + "cache_read_input_token_cost_priority": 4e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, + "cache_read_input_token_cost_flex": 1e-7, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, + "input_cost_per_token_above_272k_tokens_flex": 0.000002, + "input_cost_per_token_priority": 0.000004, + "input_cost_per_token_above_272k_tokens_priority": 0.000008, + "input_cost_per_token_flex": 0.000001, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_272k_tokens": 0.000018, + "output_cost_per_token_above_272k_tokens_flex": 0.000009, + "output_cost_per_token_priority": 0.000024, + "output_cost_per_token_above_272k_tokens_priority": 0.000036, + "output_cost_per_token_flex": 0.000006, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4138,6 +5796,55 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_272k_tokens": 0.000025, + "cache_read_input_token_cost": 0.000001, + "cache_read_input_token_cost_above_272k_tokens": 0.000002, + "input_cost_per_token": 0.00001, + "input_cost_per_token_above_272k_tokens": 0.00002, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00005, + "output_cost_per_token_above_272k_tokens": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -4294,6 +6001,43 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/gpt-chat-latest": { + "cache_read_input_token_cost": 5e-7, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 0.000005, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "azure/mistral-large-2402": { "input_cost_per_token": 0.000008, "litellm_provider": "azure", @@ -4313,7 +6057,7 @@ "supports_function_calling": true }, "azure/o1": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 0.0000075, "input_cost_per_token": 0.000015, "litellm_provider": "azure", @@ -4331,14 +6075,17 @@ }, "azure/o1-2024-12-17": { "cache_read_input_token_cost": 0.0000075, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, + "output_cost_per_token_batches": 0.00003, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4347,14 +6094,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-7, - "input_cost_per_token": 0.00000121, + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00000484, + "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4364,51 +6114,23 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": false }, - "azure/o1-preview": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": false - }, - "azure/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, - "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_vision": false - }, "azure/o3": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, "litellm_provider": "azure", @@ -4438,15 +6160,18 @@ "supports_vision": true }, "azure/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4469,7 +6194,7 @@ }, "azure/o3-deep-research": { "cache_read_input_token_cost": 0.0000025, - "deprecation_date": "2026-12-26", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.00001, "litellm_provider": "azure", "max_input_tokens": 200000, @@ -4482,6 +6207,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4506,7 +6232,7 @@ "supports_web_search": true }, "azure/o3-mini": { - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", @@ -4523,21 +6249,24 @@ }, "azure/o3-mini-2025-01-31": { "cache_read_input_token_cost": 5.5e-7, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/o3-pro": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", @@ -4547,6 +6276,7 @@ "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4568,7 +6298,7 @@ "supports_vision": true }, "azure/o3-pro-2025-06-10": { - "deprecation_date": "2026-12-17", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.00002, "input_cost_per_token_batches": 0.00001, "litellm_provider": "azure", @@ -4578,6 +6308,7 @@ "mode": "responses", "output_cost_per_token": 0.00008, "output_cost_per_token_batches": 0.00004, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4599,7 +6330,7 @@ "supports_vision": true }, "azure/o4-mini": { - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-7, "input_cost_per_token": 0.0000011, "litellm_provider": "azure", @@ -4630,14 +6361,17 @@ }, "azure/o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-7, - "deprecation_date": "2026-10-16", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -4696,11 +6430,43 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/us/codex-mini": { + "deprecation_date": "2026-11-15", + "cache_read_input_token_cost": 4.13e-7, + "input_cost_per_token": 0.00000165, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000066, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 0.0000033, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000132, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_priority": 9.63e-7, + "input_cost_per_token": 0.0000022, + "input_cost_per_token_batches": 0.0000011, + "input_cost_per_token_priority": 0.00000385, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000088, + "output_cost_per_token_batches": 0.0000044, + "output_cost_per_token_priority": 0.0000154, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_priority": 9.63e-7, "input_cost_per_token": 0.0000022, "input_cost_per_token_batches": 0.0000011, + "input_cost_per_token_priority": 0.00000385, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4708,6 +6474,8 @@ "mode": "chat", "output_cost_per_token": 0.0000088, "output_cost_per_token_batches": 0.0000044, + "output_cost_per_token_priority": 0.0000154, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4730,11 +6498,27 @@ "supports_vision": true, "supports_web_search": false }, + "azure/us/gpt-4.1-mini": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 1.1e-7, + "cache_read_input_token_cost_priority": 1.93e-7, + "input_cost_per_token": 4.4e-7, + "input_cost_per_token_batches": 2.2e-7, + "input_cost_per_token_priority": 7.7e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.00000176, + "output_cost_per_token_batches": 8.8e-7, + "output_cost_per_token_priority": 0.00000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-7, + "cache_read_input_token_cost_priority": 1.93e-7, "input_cost_per_token": 4.4e-7, "input_cost_per_token_batches": 2.2e-7, + "input_cost_per_token_priority": 7.7e-7, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4742,6 +6526,8 @@ "mode": "chat", "output_cost_per_token": 0.00000176, "output_cost_per_token_batches": 8.8e-7, + "output_cost_per_token_priority": 0.00000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4764,11 +6550,22 @@ "supports_vision": true, "supports_web_search": false }, + "azure/us/gpt-4.1-nano": { + "deprecation_date": "2027-04-14", + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 1.1e-7, + "input_cost_per_token_batches": 5.5e-8, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 1.1e-7, - "input_cost_per_token_batches": 6e-8, + "input_cost_per_token_batches": 5.5e-8, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -4776,6 +6573,7 @@ "mode": "chat", "output_cost_per_token": 4.4e-7, "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4797,16 +6595,29 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", + "input_cost_per_token": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000165, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/gpt-4o-2024-08-06": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, + "input_cost_per_token_batches": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4817,13 +6628,17 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 0.00000138, + "cache_read_input_token_cost": 0.000001375, "input_cost_per_token": 0.00000275, + "input_cost_per_token_batches": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4834,12 +6649,14 @@ "cache_read_input_token_cost": 8.3e-8, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-7, + "input_cost_per_token_batches": 8.3e-8, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4847,16 +6664,37 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-5": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_batches": 6.875e-8, + "cache_read_input_token_cost_priority": 2.75e-7, + "input_cost_per_token": 0.000001375, + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_priority": 2.75e-7, "deprecation_date": "2027-02-09", "input_cost_per_token": 0.000001375, + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000011, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4878,18 +6716,49 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-8 + }, + "azure/us/gpt-5-codex": { + "deprecation_date": "2027-03-17", + "cache_read_input_token_cost": 1.38e-7, + "input_cost_per_token": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000011, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 2.75e-8, + "cache_read_input_token_cost_batches": 1.375e-8, + "cache_read_input_token_cost_priority": 4.95e-8, + "input_cost_per_token": 2.75e-7, + "input_cost_per_token_batches": 1.375e-7, + "input_cost_per_token_priority": 4.95e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000022, + "output_cost_per_token_batches": 0.0000011, + "output_cost_per_token_priority": 0.00000396, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-8, + "cache_read_input_token_cost_priority": 4.95e-8, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-7, + "input_cost_per_token_batches": 1.375e-7, + "input_cost_per_token_priority": 4.95e-7, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000022, + "output_cost_per_token_batches": 0.0000011, + "output_cost_per_token_priority": 0.00000396, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4911,18 +6780,34 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-8 + }, + "azure/us/gpt-5-nano": { + "deprecation_date": "2027-02-09", + "cache_read_input_token_cost": 5.5e-9, + "cache_read_input_token_cost_batches": 2.75e-9, + "input_cost_per_token": 5.5e-8, + "input_cost_per_token_batches": 2.75e-8, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-9, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-8, + "input_cost_per_token_batches": 2.75e-8, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4944,12 +6829,25 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-9 + }, + "azure/us/gpt-5-pro": { + "deprecation_date": "2027-04-07", + "input_cost_per_token": 0.0000165, + "input_cost_per_token_batches": 0.00000825, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 0.000066, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-7, - "input_cost_per_token": 0.00000138, + "cache_read_input_token_cost": 1.375e-7, + "cache_read_input_token_cost_batches": 6.875e-8, + "cache_read_input_token_cost_priority": 2.75e-7, + "input_cost_per_token": 0.000001375, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -4980,18 +6878,83 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-7, + "input_cost_per_token_priority": 0.00000275, + "output_cost_per_token_batches": 0.0000055, + "output_cost_per_token_priority": 0.000022, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", + "cache_read_input_token_cost": 1.375e-7, + "input_cost_per_token": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000011, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 0.00000138, + "azure/us/gpt-5.2": { + "deprecation_date": "2027-06-08", + "cache_read_input_token_cost": 1.925e-7, + "cache_read_input_token_cost_batches": 9.625e-8, + "cache_read_input_token_cost_priority": 3.85e-7, + "input_cost_per_token": 0.000001925, + "input_cost_per_token_batches": 9.625e-7, + "input_cost_per_token_priority": 0.00000385, "litellm_provider": "azure", - "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000154, + "output_cost_per_token_batches": 0.0000077, + "output_cost_per_token_priority": 0.0000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", + "cache_read_input_token_cost": 1.925e-7, + "input_cost_per_token": 0.000001925, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000154, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 0.0000231, + "input_cost_per_token_batches": 0.00001155, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 0.0000924, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", + "cache_read_input_token_cost": 1.925e-7, + "cache_read_input_token_cost_priority": 3.85e-7, + "input_cost_per_token": 0.000001925, + "input_cost_per_token_priority": 0.00000385, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0000154, + "output_cost_per_token_priority": 0.0000308, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4": { + "deprecation_date": "2027-09-02", + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-7, + "cache_read_input_token_cost_batches": 1.43e-7, + "cache_read_input_token_cost_priority": 5.5e-7, + "input_cost_per_token": 0.00000275, + "input_cost_per_token_priority": 0.0000055, + "output_cost_per_token": 0.0000165, + "output_cost_per_token_priority": 0.000033, + "litellm_provider": "azure", + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000011, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5002,8 +6965,7 @@ "image" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": true, "supports_native_streaming": true, @@ -5016,12 +6978,22 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 0.0000055, + "input_cost_per_token_above_272k_tokens_batches": 0.00000275, + "input_cost_per_token_batches": 0.000001375, + "output_cost_per_token_above_272k_tokens": 0.00002475, + "output_cost_per_token_above_272k_tokens_batches": 0.000012375, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": true }, - "azure/us/gpt-5.4": { - "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-7, + "azure/us/gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, "cache_read_input_token_cost_priority": 5.5e-7, + "deprecation_date": "2027-09-02", "input_cost_per_token": 0.00000275, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token": 0.0000165, @@ -5055,22 +7027,87 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 0.0000055, + "input_cost_per_token_batches": 0.000001375, + "output_cost_per_token_above_272k_tokens": 0.00002475, + "output_cost_per_token_batches": 0.00000825, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-7, + "cache_read_input_token_cost_batches": 1.43e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.00000275, + "output_cost_per_token_above_272k_tokens_batches": 0.000012375 }, - "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-7, - "cache_read_input_token_cost_priority": 5.5e-7, - "deprecation_date": "2027-09-02", - "input_cost_per_token": 0.00000275, - "input_cost_per_token_priority": 0.0000055, - "output_cost_per_token": 0.0000165, - "output_cost_per_token_priority": 0.000033, + "azure/us/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 8.25e-8, + "cache_read_input_token_cost_batches": 4.125e-8, + "cache_read_input_token_cost_priority": 1.65e-7, + "input_cost_per_token": 8.25e-7, + "input_cost_per_token_batches": 4.125e-7, + "input_cost_per_token_priority": 0.00000165, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.00000495, + "output_cost_per_token_batches": 0.000002475, + "output_cost_per_token_priority": 0.0000099, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", + "cache_read_input_token_cost": 2.2e-8, + "cache_read_input_token_cost_batches": 1.1e-8, + "input_cost_per_token": 2.2e-7, + "input_cost_per_token_batches": 1.1e-7, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000001375, + "output_cost_per_token_batches": 6.875e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", + "input_cost_per_token": 0.000033, + "input_cost_per_token_above_272k_tokens": 0.000066, + "input_cost_per_token_above_272k_tokens_batches": 0.000033, + "input_cost_per_token_batches": 0.0000165, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_above_272k_tokens_batches": 0.0001485, + "output_cost_per_token_batches": 0.000099, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.5": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.0000011, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "cache_read_input_token_cost_priority": 0.000001375, + "input_cost_per_token": 0.0000055, + "input_cost_per_token_above_272k_tokens": 0.000011, + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "input_cost_per_token_priority": 0.00001375, + "output_cost_per_token": 0.000033, + "output_cost_per_token_above_272k_tokens": 0.0000495, + "output_cost_per_token_priority": 0.0000825, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_batches": 0.00002475, + "output_cost_per_token_batches": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5093,16 +7130,17 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, + "supports_web_search": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, - "azure/us/gpt-5.5": { - "deprecation_date": "2027-10-26", + "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_priority": 0.00000138, + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token": 0.0000055, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, @@ -5142,18 +7180,24 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": true, - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "input_cost_per_token_batches": 0.00000275, + "output_cost_per_token_above_272k_tokens_batches": 0.00002475, + "output_cost_per_token_batches": 0.0000165, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/gpt-5.5-2026-04-23": { + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_priority": 0.00000138, + "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token": 0.0000055, + "input_cost_per_token_batches": 0.00000275, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token": 0.000033, + "output_cost_per_token_batches": 0.0000165, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "litellm_provider": "azure", @@ -5189,7 +7233,14 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, + "cache_read_input_token_cost_batches": 2.75e-7, + "input_cost_per_token_above_272k_tokens_batches": 0.0000055, + "output_cost_per_token_above_272k_tokens_batches": 0.00002475 }, "azure/us/gpt-5.6": { "cache_creation_input_token_cost": 0.000006875, @@ -5273,6 +7324,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5301,33 +7353,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, - "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, - "cache_creation_input_token_cost_priority": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, - "cache_read_input_token_cost_priority": 0.0000011, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_272k_tokens": 0.000011, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, + "cache_creation_input_token_cost_priority": 0.000011, + "cache_read_input_token_cost": 4.4e-7, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, + "cache_read_input_token_cost_priority": 8.8e-7, "deprecation_date": "2028-01-11", - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "input_cost_per_token_above_272k_tokens_priority": 0.000022, - "input_cost_per_token_priority": 0.000011, + "input_cost_per_token": 0.0000044, + "input_cost_per_token_above_272k_tokens": 0.0000088, + "input_cost_per_token_above_272k_tokens_priority": 0.0000176, + "input_cost_per_token_priority": 0.0000088, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, - "output_cost_per_token_above_272k_tokens_priority": 0.000099, - "output_cost_per_token_priority": 0.000066, + "output_cost_per_token": 0.000022, + "output_cost_per_token_above_272k_tokens": 0.000033, + "output_cost_per_token_above_272k_tokens_priority": 0.000066, + "output_cost_per_token_priority": 0.000044, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5383,6 +7436,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5429,6 +7483,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -5457,62 +7512,102 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/us/gpt-chat-latest": { + "cache_read_input_token_cost": 5.5e-7, + "deprecation_date": "2026-12-02", + "input_cost_per_token": 0.0000055, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000033, + "reasoning_effort_levels": [ + "medium" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 0.00000825, - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.0000165, + "input_cost_per_token_batches": 0.00000825, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000066, + "output_cost_per_token_batches": 0.000033, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_vision": true }, - "azure/us/o1-mini-2024-09-12": { + "azure/us/o1-mini": { "cache_read_input_token_cost": 6.05e-7, "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_vision": false + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, - "azure/us/o1-preview-2024-09-12": { - "cache_read_input_token_cost": 0.00000825, - "input_cost_per_token": 0.0000165, + "azure/us/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 128000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000066, + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_vision": false }, "azure/us/o3-2025-04-16": { - "deprecation_date": "2026-10-21", + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000022, + "input_cost_per_token_batches": 0.0000011, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000088, + "output_cost_per_token_batches": 0.0000044, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5533,9 +7628,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o3-deep-research": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000044, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-7, - "deprecation_date": "2026-10-01", + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.00000121, "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", @@ -5545,21 +7649,25 @@ "mode": "chat", "output_cost_per_token": 0.00000484, "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-7, - "deprecation_date": "2026-10-16", + "cache_read_input_token_cost": 3.03e-7, + "deprecation_date": "2026-11-19", "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -5576,7 +7684,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5598,7 +7706,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000132, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5614,7 +7722,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000185, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5629,7 +7737,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 0.000003828, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5645,7 +7753,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00000352, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5661,7 +7769,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00000484, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5676,37 +7784,37 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00000484, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-7, - "input_cost_per_token": 0.0000021, + "cache_read_input_token_cost": 2.31e-7, + "input_cost_per_token": 0.00000231, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000066, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 0.00000726, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { - "cache_read_input_token_cost": 1.7e-7, - "input_cost_per_token": 0.000001, + "cache_read_input_token_cost": 1.9e-7, + "input_cost_per_token": 0.0000011, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 0.00000405, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token": 0.00000446, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -5728,7 +7836,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000033, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -5751,7 +7859,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -5774,7 +7882,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -5789,20 +7897,20 @@ "supports_vision": true }, "azure_ai/FW-Kimi-K3": { - "cache_read_input_token_cost": 3.3e-7, - "input_cost_per_token": 0.0000033, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000165, + "output_cost_per_token": 0.000015, "reasoning_effort_levels": [ "low", "high", "max" ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -5826,7 +7934,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.00000132, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -5841,7 +7949,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 0.00000132, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -5856,15 +7964,15 @@ "supports_vision": true }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { - "cache_read_input_token_cost": 1.19e-7, - "input_cost_per_token": 6e-7, + "cache_read_input_token_cost": 1.3e-7, + "input_cost_per_token": 6.6e-7, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.0000024, - "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", + "output_cost_per_token": 0.00000264, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -5883,7 +7991,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -5896,34 +8004,6 @@ "supports_tool_choice": true, "supports_vision": false }, - "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3.7e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 3.7e-7, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 0.00000204, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.00000204, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "azure_ai/Llama-3.3-70B-Instruct": { "input_cost_per_token": 7.1e-7, "litellm_provider": "azure_ai", @@ -5932,19 +8012,19 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-7, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 0.00000141, + "input_cost_per_token": 2.5e-7, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-7, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 0.000001, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -5970,7 +8050,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000054, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -5983,7 +8063,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.000008, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -6008,18 +8088,6 @@ "output_cost_per_token": 3.7e-7, "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 0.00000533, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 0.000016, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { "input_cost_per_token": 0.00000268, "litellm_provider": "azure_ai", @@ -6031,18 +8099,6 @@ "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-06-13", - "input_cost_per_token": 3e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.1e-7, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, "azure_ai/Phi-3-medium-128k-instruct": { "input_cost_per_token": 1.7e-7, "litellm_provider": "azure_ai", @@ -6051,7 +8107,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6063,7 +8119,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6075,7 +8131,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6087,7 +8143,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6099,7 +8155,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6111,7 +8167,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6123,7 +8179,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6135,7 +8191,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -6147,7 +8203,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -6159,7 +8215,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-7, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -6172,18 +8228,18 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-7, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-8, + "input_cost_per_token": 7.5e-8, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-7, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -6195,7 +8251,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-7, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true @@ -6208,7 +8264,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -6306,29 +8362,6 @@ "supports_vision": true, "prompt_cache_min_tokens": 4096 }, - "azure_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "azure_ai", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "azure_ai/claude-opus-4-5": { "deprecation_date": "2026-10-19", "cache_creation_input_token_cost": 0.00000625, @@ -6483,6 +8516,41 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512 }, + "azure_ai/claude-opus-5-5": { + "supports_mid_conversation_system": true, + "input_cost_per_token": 0.000004, + "output_cost_per_token": 0.00002, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 + }, "azure_ai/claude-sonnet-4-5": { "deprecation_date": "2026-10-19", "cache_creation_input_token_cost": 0.00000375, @@ -6574,23 +8642,10 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 0.00001, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, - "azure_ai/deepseek-r1": { - "deprecation_date": "2026-08-13", - "input_cost_per_token": 0.00000135, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0000054, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", - "supports_reasoning": true, - "supports_tool_choice": true - }, "azure_ai/deepseek-v3": { "input_cost_per_token": 0.00000114, "litellm_provider": "azure_ai", @@ -6599,34 +8654,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00000456, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3-0324": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 0.00000114, - "litellm_provider": "azure_ai", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.00000456, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/deepseek-v3.1": { - "deprecation_date": "2026-07-13", - "input_cost_per_token": 0.00000123, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.00000494, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", - "supports_function_calling": true, - "supports_reasoning": true, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3.2": { @@ -6637,7 +8665,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000168, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -6652,7 +8680,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.00000168, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -6668,7 +8696,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-7, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -6684,44 +8712,13 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 0.00000348, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "cache_read_input_token_cost": 1.45e-7, "supports_prompt_caching": true }, - "azure_ai/global/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 0.000003, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/global/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.00000127, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-7, @@ -7079,6 +9076,53 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "cache_read_input_token_cost_priority": 0.000001, + "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.00001, + "input_cost_per_token_priority": 0.00001, + "input_cost_per_token_above_272k_tokens_priority": 0.00002, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "output_cost_per_token_above_272k_tokens": 0.000045, + "output_cost_per_token_priority": 0.00006, + "output_cost_per_token_above_272k_tokens_priority": 0.00009, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-6-astra": { "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, @@ -7170,43 +9214,12 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true }, - "azure_ai/grok-3": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 0.000003, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-3-mini": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.00000127, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4": { "input_cost_per_token": 0.000003, "litellm_provider": "azure_ai", @@ -7215,7 +9228,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -7229,7 +9242,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -7243,7 +9256,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -7260,8 +9273,9 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -7277,53 +9291,28 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "supports_reasoning": true }, - "azure_ai/grok-4-fast-non-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "azure_ai/grok-4-fast-reasoning": { - "deprecation_date": "2026-05-01", - "input_cost_per_token": 2e-7, - "output_cost_per_token": 5e-7, - "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_web_search": true - }, "azure_ai/grok-4.3": { "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", + "output_cost_per_token_above_200k_tokens": 0.000005, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -7334,14 +9323,17 @@ }, "azure_ai/grok-4.6": { "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000006, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", + "output_cost_per_token_above_200k_tokens": 0.000012, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -7358,7 +9350,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000015, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -7393,7 +9385,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000003, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -7410,7 +9402,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -7435,7 +9427,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -7492,7 +9484,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0000015, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -7597,6 +9589,74 @@ "mode": "chat", "output_cost_per_token": 0.0000015 }, + "baseten/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 1.3e-7, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.6e-7, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.45e-7, + "input_cost_per_token": 0.00000174, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.00000348, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.32e-7, + "input_cost_per_token": 0.00000132, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.00000396, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 7e-9, + "input_cost_per_token": 3e-7, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { "input_cost_per_token": 6e-7, "litellm_provider": "baseten", @@ -7615,6 +9675,74 @@ "mode": "chat", "output_cost_per_token": 0.000003 }, + "baseten/moonshotai/Kimi-K2.6": { + "cache_read_input_token_cost": 1.6e-7, + "input_cost_per_token": 9.5e-7, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.6e-7, + "input_cost_per_token": 9.5e-7, + "litellm_provider": "baseten", + "max_input_tokens": 262000, + "max_output_tokens": 262000, + "max_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "cache_read_input_token_cost": 1.2e-7, + "input_cost_per_token": 6e-7, + "litellm_provider": "baseten", + "max_input_tokens": 202800, + "max_output_tokens": 202800, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "baseten/nvidia/Nemotron-120B-A12B": { "input_cost_per_token": 3e-7, "litellm_provider": "baseten", @@ -7622,10 +9750,55 @@ "output_cost_per_token": 7.5e-7 }, "baseten/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 1e-7, "litellm_provider": "baseten", + "max_input_tokens": 128072, + "max_output_tokens": 128072, + "max_tokens": 128072, "mode": "chat", - "output_cost_per_token": 5e-7 + "output_cost_per_token": 5e-7, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "baseten/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.7e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00000405, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/thinkingmachines/inkling-small": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 5e-7, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "baseten/zai-org/GLM-4.6": { "input_cost_per_token": 6e-7, @@ -7634,10 +9807,21 @@ "output_cost_per_token": 0.0000022 }, "baseten/zai-org/GLM-4.7": { + "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 6e-7, "litellm_provider": "baseten", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 0.0000022 + "output_cost_per_token": 0.0000022, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false }, "baseten/zai-org/GLM-5": { "input_cost_per_token": 9.5e-7, @@ -7645,6 +9829,40 @@ "mode": "chat", "output_cost_per_token": 0.00000315 }, + "baseten/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.0000014, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/zai-org/GLM-5.2-Fast": { + "cache_read_input_token_cost": 2.1e-7, + "input_cost_per_token": 0.0000021, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000066, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "baseten/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.0000014, @@ -7654,7 +9872,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://www.baseten.co/pricing/", + "source": "https://inference.baseten.co/v1/models", "supported_modalities": [ "text", "image" @@ -7664,6 +9882,24 @@ ], "supports_function_calling": true, "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true @@ -7875,6 +10111,19 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000145, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", @@ -7972,6 +10221,19 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000141, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { "input_cost_per_token": 3.09e-7, "litellm_provider": "bedrock", @@ -7986,6 +10248,19 @@ "supports_tool_choice": true, "output_cost_per_token": 0.000001236 }, + "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.545e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001236, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-7, "litellm_provider": "bedrock", @@ -8352,6 +10627,19 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000141, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 0.00000345, "litellm_provider": "bedrock", @@ -8397,6 +10685,23 @@ "supports_tool_choice": true, "output_cost_per_token": 0.00000186 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.00000101, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-7, "litellm_provider": "bedrock", @@ -8410,6 +10715,19 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 2.3e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000186, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock", @@ -8582,6 +10900,19 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { + "input_cost_per_token": 1.8e-7, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000145, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_system_messages": true + }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { "input_cost_per_second": 0.011, "litellm_provider": "bedrock", @@ -8891,6 +11222,7 @@ "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 9.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 300000, @@ -8932,40 +11264,6 @@ "mode": "chat", "output_cost_per_token": 0.0000015 }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.0000036, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000018, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-7, - "cache_creation_input_token_cost": 0.0000045 - }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7 - }, "bedrock/us-gov-east-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 0.000015, "cache_creation_input_token_cost_above_1hr": 0.000024, @@ -9033,6 +11331,7 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9064,6 +11363,7 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9088,6 +11388,41 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true }, + "bedrock/us-gov-east-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 0.000006, + "cache_creation_input_token_cost_above_1hr": 0.0000096, + "cache_read_input_token_cost": 2.4e-7, + "input_cost_per_token": 0.0000048, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.0000045, "cache_creation_input_token_cost_above_1hr": 0.0000072, @@ -9121,6 +11456,7 @@ "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000024, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9266,6 +11602,7 @@ "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.8e-8, "input_cost_per_token": 7.2e-8, "litellm_provider": "bedrock", "max_input_tokens": 300000, @@ -9281,6 +11618,7 @@ "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 1.05e-8, "input_cost_per_token": 4.2e-8, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -9294,6 +11632,7 @@ "supports_tool_choice": true }, "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 9.6e-7, "litellm_provider": "bedrock", "max_input_tokens": 300000, @@ -9335,61 +11674,6 @@ "mode": "chat", "output_cost_per_token": 0.0000015 }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.0000036, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000018, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3.6e-7, - "cache_creation_input_token_cost": 0.0000045 - }, - "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { - "cache_creation_input_token_cost": 0.0000045, - "cache_read_input_token_cost": 3.6e-7, - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.0000036, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000018, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7 - }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 0.000015, "cache_creation_input_token_cost_above_1hr": 0.000024, @@ -9457,6 +11741,7 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9488,6 +11773,7 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9512,6 +11798,41 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true }, + "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 0.000006, + "cache_creation_input_token_cost_above_1hr": 0.0000096, + "cache_read_input_token_cost": 2.4e-7, + "input_cost_per_token": 0.0000048, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.0000045, "cache_creation_input_token_cost_above_1hr": 0.0000072, @@ -9545,6 +11866,7 @@ "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000024, "litellm_provider": "bedrock", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -9936,6 +12258,34 @@ "supports_tool_choice": true, "prompt_cache_min_tokens": 2048 }, + "bedrock_mantle/anthropic.claude-haiku-4-5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_native_structured_output": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 4096, + "input_cost_per_token_batches": 5e-7, + "output_cost_per_token_batches": 0.0000025 + }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, @@ -10025,22 +12375,25 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, "supports_web_search": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 0.0000055, - "input_cost_per_token_above_272k_tokens": 0.000011, - "cache_creation_input_token_cost": 0.000006875, - "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, - "cache_read_input_token_cost": 5.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 0.0000011, - "output_cost_per_token": 0.000033, - "output_cost_per_token_above_272k_tokens": 0.0000495, + "input_cost_per_token": 0.0000044, + "input_cost_per_token_above_272k_tokens": 0.0000088, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_272k_tokens": 0.000011, + "cache_read_input_token_cost": 4.4e-7, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, + "output_cost_per_token": 0.000022, + "output_cost_per_token_above_272k_tokens": 0.000033, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, @@ -10064,11 +12417,14 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, "supports_web_search": true }, "bedrock_mantle/openai.gpt-5.6-terra": { @@ -10103,11 +12459,14 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, + "supports_xhigh_reasoning_effort": true, "supports_web_search": true }, "bedrock_mantle/openai.gpt-6-astra": { @@ -10137,10 +12496,14 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" }, @@ -10345,10 +12708,12 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 2.64e-7, "input_cost_per_token_above_272k_tokens": 5.28e-7, @@ -10378,10 +12743,12 @@ "text" ], "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true, "input_cost_per_token": 0.00000264, "input_cost_per_token_above_272k_tokens": 0.00000528, @@ -10431,7 +12798,7 @@ "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -10476,7 +12843,7 @@ "output_cost_per_token": 0.0000025, "cache_read_input_token_cost": 2e-7, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -10589,33 +12956,21 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "cerebras/zai-glm-4.6": { - "deprecation_date": "2026-01-20", - "input_cost_per_token": 0.00000225, - "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00000275, - "source": "https://www.cerebras.ai/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "cerebras/zai-glm-4.7": { - "deprecation_date": "2026-08-17", - "input_cost_per_token": 0.00000225, + "cerebras/qwen-3.8-27b": { + "input_cost_per_token": 9.9e-7, "litellm_provider": "cerebras", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.00000275, - "source": "https://www.cerebras.ai/pricing", + "output_cost_per_token": 0.00000149, + "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "chat-latest": { "cache_read_input_token_cost": 5e-7, @@ -10629,7 +12984,7 @@ "reasoning_effort_levels": [ "medium" ], - "source": "https://developers.openai.com/api/docs/models/chat-latest", + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -10662,23 +13017,6 @@ "mode": "chat", "output_cost_per_token": 5e-7 }, - "chatgpt-4o-latest": { - "deprecation_date": "2026-02-17", - "input_cost_per_token": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "chatgpt/gpt-5.2": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, @@ -10803,133 +13141,8 @@ "supports_response_schema": true, "supports_vision": true }, - "claude-3-7-sonnet-20250219": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2026-02-19", - "input_cost_per_token": 0.000003, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "claude-3-haiku-20240307": { - "cache_creation_input_token_cost": 3e-7, - "cache_creation_input_token_cost_above_1hr": 5e-7, - "cache_read_input_token_cost": 3e-8, - "deprecation_date": "2026-04-20", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-3-opus-20240229": { - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "deprecation_date": "2026-01-05", - "input_cost_per_token": 0.000015, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "claude-4-opus-20250514": { - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 0.000015, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-4-sonnet-20250514": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "deprecation_date": "2026-06-15", - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "prompt_cache_min_tokens": 1024 - }, "claude-fable-5": { - "deprecation_date": "2027-06-09", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_1hr": 0.00002, "cache_read_input_token_cost": 0.000001, @@ -10966,10 +13179,10 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { - "deprecation_date": "2027-09-01", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_1hr": 0.00002, "cache_read_input_token_cost": 2.5e-7, @@ -11007,10 +13220,9 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/fable-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-haiku-4-5": { - "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, @@ -11031,10 +13243,10 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-haiku-4-5-20251001": { - "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 0.00000125, "cache_creation_input_token_cost_above_1hr": 0.000002, "cache_read_input_token_cost": 1e-7, @@ -11058,6 +13270,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-mythos-5": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_1hr": 0.00002, "cache_read_input_token_cost": 0.000001, @@ -11074,7 +13287,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://platform.claude.com/docs/en/about-claude/models/overview", + "source": "https://platform.claude.com/docs/en/about-claude/pricing", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, @@ -11097,7 +13310,7 @@ } }, "claude-mythos-5-1": { - "deprecation_date": "2027-09-01", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_1hr": 0.00002, "cache_read_input_token_cost": 2.5e-7, @@ -11135,9 +13348,10 @@ "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, - "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-mythos-preview": { + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000125, "cache_creation_input_token_cost_above_1hr": 0.00002, "cache_read_input_token_cost": 0.000001, @@ -11175,94 +13389,7 @@ "us": 1.1 } }, - "claude-opus-4-1": { - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "deprecation_date": "2026-08-05" - }, - "claude-opus-4-1-20250805": { - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "deprecation_date": "2026-08-05", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_native_structured_output": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "claude-opus-4-20250514": { - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "deprecation_date": "2026-06-15", - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "claude-opus-4-5": { - "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11283,16 +13410,17 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-5-20251101": { - "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11313,6 +13441,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11322,7 +13451,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-6": { - "deprecation_date": "2027-02-05", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11345,6 +13474,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11356,10 +13486,11 @@ "supports_output_config": true, "supports_max_reasoning_effort": true, "supports_speed": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6-20260205": { - "deprecation_date": "2027-02-05", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11382,6 +13513,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11396,7 +13528,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { - "deprecation_date": "2027-04-16", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11418,6 +13550,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11431,10 +13564,11 @@ }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-7-20260416": { - "deprecation_date": "2027-04-16", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11456,6 +13590,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11472,7 +13607,7 @@ "prompt_cache_min_tokens": 2048 }, "claude-opus-4-8": { - "deprecation_date": "2027-05-28", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11495,6 +13630,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11509,10 +13645,12 @@ }, "supports_output_config": true, "supports_speed": true, - "prompt_cache_min_tokens": 1024 + "supports_fast_mode": true, + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5": { - "deprecation_date": "2027-07-24", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000625, "cache_creation_input_token_cost_above_1hr": 0.00001, "cache_read_input_token_cost": 5e-7, @@ -11535,6 +13673,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11549,43 +13688,54 @@ }, "supports_output_config": true, "supports_speed": true, + "supports_fast_mode": true, "prompt_cache_min_tokens": 512, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, - "claude-sonnet-4-20250514": { - "deprecation_date": "2026-06-15", - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "claude-opus-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2 + }, + "supports_output_config": true, + "supports_speed": true, + "supports_fast_mode": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5": { - "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, @@ -11596,7 +13746,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -11616,10 +13766,10 @@ "supports_native_structured_output": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-4-5-20250929": { - "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, @@ -11630,7 +13780,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -11651,7 +13801,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.00000375, @@ -11685,7 +13836,7 @@ "output_cost_per_token_batches": 0.0000075 }, "claude-sonnet-4-6": { - "deprecation_date": "2027-02-17", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.00000375, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_read_input_token_cost": 3e-7, @@ -11708,6 +13859,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_native_structured_output": true, @@ -11718,10 +13870,11 @@ "prompt_cache_min_tokens": 1024, "provider_specific_entry": { "us": 1.1 - } + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-sonnet-5": { - "deprecation_date": "2027-06-30", + "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 0.0000025, "cache_creation_input_token_cost_above_1hr": 0.000004, "cache_read_input_token_cost": 2e-7, @@ -11745,6 +13898,7 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_thinking_cache_preservation": true, "supports_reasoning": true, "supports_response_schema": true, "supports_sampling_params": false, @@ -11757,7 +13911,7 @@ }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview" + "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "input_cost_per_token": 3.51e-7, @@ -12151,28 +14305,6 @@ "output_cost_per_token": 6e-7, "supports_tool_choice": true }, - "cohere.command-r-plus-v1:0": { - "deprecation_date": "2026-08-19", - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_tool_choice": true - }, - "cohere.command-r-v1:0": { - "deprecation_date": "2026-08-19", - "input_cost_per_token": 5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_tool_choice": true - }, "cohere.command-text-v14": { "input_cost_per_token": 0.0000015, "litellm_provider": "bedrock", @@ -12194,28 +14326,20 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-light": { - "input_cost_per_token": 3e-7, - "litellm_provider": "cohere_chat", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, - "command-r": { - "input_cost_per_token": 1.5e-7, + "command-a-plus-05-2026": { + "input_cost_per_token": 0, "litellm_provider": "cohere_chat", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 6e-7, + "output_cost_per_token": 0, + "source": "https://docs.cohere.com/docs/command-a-plus", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "deprecation_date": "2025-09-15" + "supports_vision": true }, "command-r-08-2024": { "input_cost_per_token": 1.5e-7, @@ -12228,18 +14352,6 @@ "supports_function_calling": true, "supports_tool_choice": true }, - "command-r-plus": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "cohere_chat", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_function_calling": true, - "supports_tool_choice": true, - "deprecation_date": "2025-09-15" - }, "command-r-plus-08-2024": { "input_cost_per_token": 0.0000025, "litellm_provider": "cohere_chat", @@ -12265,7 +14377,7 @@ }, "computer-use-preview": { "input_cost_per_token": 0.000003, - "litellm_provider": "azure", + "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, @@ -12283,12 +14395,14 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "source": "https://platform.openai.com/docs/models/computer-use-preview" }, "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507": { "input_cost_per_token": 0.000003, @@ -13306,6 +15420,26 @@ } ] }, + "dashscope/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-7, + "cache_read_input_token_cost": 1.6e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-7, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "dashscope/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-7, "input_cost_per_token": 0.000002, @@ -13323,6 +15457,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "dashscope/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-7, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-7, "litellm_provider": "dashscope", @@ -13336,29 +15490,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "databricks/databricks-claude-3-7-sonnet": { - "cache_creation_input_token_cost": 0.00000374997, - "cache_read_input_token_cost": 3.0002e-7, - "deprecation_date": "2026-04-12", - "input_cost_per_token": 0.0000029999900000000002, - "input_dbu_cost_per_token": 0.000042857, - "litellm_provider": "databricks", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.000015000020000000002, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "databricks/databricks-claude-fable-5": { "cache_creation_input_token_cost": 0.00001250004, "cache_read_input_token_cost": 0.00000100002, @@ -13382,6 +15513,7 @@ "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": false, @@ -13411,6 +15543,7 @@ "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, @@ -13436,6 +15569,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096 }, @@ -13459,6 +15593,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, @@ -13482,6 +15617,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, @@ -13505,6 +15641,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096 @@ -13530,6 +15667,7 @@ "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096 }, @@ -13555,6 +15693,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true @@ -13582,6 +15721,7 @@ "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true @@ -13609,6 +15749,7 @@ "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true @@ -13635,6 +15776,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { @@ -13657,6 +15799,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-5": { @@ -13679,6 +15822,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, @@ -13703,6 +15847,7 @@ "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024 }, @@ -13729,6 +15874,7 @@ "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true @@ -13807,8 +15953,22 @@ "output_dbu_cost_per_token": 0.000035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, + "supports_anthropic_thinking_payload": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-2-5-pro": { "cache_creation_input_token_cost": 0.00000124999, @@ -13827,8 +15987,23 @@ "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, + "supports_anthropic_thinking_payload": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "deprecation_date": "2026-10-02", + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-1-flash-image": { "litellm_provider": "databricks", @@ -13869,7 +16044,19 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 0.00000249998, @@ -13889,7 +16076,20 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_reasoning": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 0.00000187502, @@ -14051,7 +16251,19 @@ "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-pro": { "cache_creation_input_token_cost": 0.00000249998, @@ -14240,44 +16452,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-1-codex-max": { - "cache_creation_input_token_cost": 0.00000124999, - "cache_read_input_token_cost": 1.2502e-7, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 0.00000124999, - "input_dbu_cost_per_token": 0.000017857, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.000009999990000000002, - "output_dbu_cost_per_token": 0.000142857, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, - "databricks/databricks-gpt-5-1-codex-mini": { - "cache_creation_input_token_cost": 2.4997e-7, - "cache_read_input_token_cost": 2.499e-8, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 2.4997e-7, - "input_dbu_cost_per_token": 0.000003571, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.00000199997, - "output_dbu_cost_per_token": 0.000028571, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-2": { "cache_creation_input_token_cost": 0.00000175, "cache_read_input_token_cost": 1.75e-7, @@ -14298,25 +16472,6 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, - "databricks/databricks-gpt-5-2-codex": { - "cache_creation_input_token_cost": 0.00000175, - "cache_read_input_token_cost": 1.75e-7, - "deprecation_date": "2026-07-16", - "input_cost_per_token": 0.00000175, - "input_dbu_cost_per_token": 0.000025, - "litellm_provider": "databricks", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.000014, - "output_dbu_cost_per_token": 0.0002, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true - }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 0.00000249998, "cache_read_input_token_cost": 2.4997e-7, @@ -14648,25 +16803,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "databricks/databricks-llama-2-70b-chat": { - "cache_creation_input_token_cost": 5.0001e-7, - "cache_read_input_token_cost": 5.0001e-7, - "deprecation_date": "2024-10-30", - "input_cost_per_token": 5.0001e-7, - "input_dbu_cost_per_token": 0.000007143, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.0000015000300000000002, - "output_dbu_cost_per_token": 0.000021429, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-llama-4-maverick": { "cache_creation_input_token_cost": 5.0001e-7, "cache_read_input_token_cost": 5.0001e-7, @@ -14685,25 +16821,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "cache_creation_input_token_cost": 0.00000500003, - "cache_read_input_token_cost": 0.00000500003, - "deprecation_date": "2026-02-15", - "input_cost_per_token": 0.00000500003, - "input_dbu_cost_per_token": 0.000071429, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.000015000020000000002, - "output_dbu_cost_per_token": 0.000214286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-meta-llama-3-1-8b-instruct": { "cache_creation_input_token_cost": 1.5001e-7, "cache_read_input_token_cost": 1.5001e-7, @@ -14739,82 +16856,6 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "cache_creation_input_token_cost": 0.00000100002, - "cache_read_input_token_cost": 0.00000100002, - "deprecation_date": "2024-07-23", - "input_cost_per_token": 0.00000100002, - "input_dbu_cost_per_token": 0.000014286, - "litellm_provider": "databricks", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.0000029999900000000002, - "output_dbu_cost_per_token": 0.000042857, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mixtral-8x7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-7, - "cache_read_input_token_cost": 5.0001e-7, - "deprecation_date": "2025-04-30", - "input_cost_per_token": 5.0001e-7, - "input_dbu_cost_per_token": 0.000007143, - "litellm_provider": "databricks", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.00000100002, - "output_dbu_cost_per_token": 0.000014286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-30b-instruct": { - "cache_creation_input_token_cost": 0.00000100002, - "cache_read_input_token_cost": 0.00000100002, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 0.00000100002, - "input_dbu_cost_per_token": 0.000014286, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0.00000100002, - "output_dbu_cost_per_token": 0.000014286, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "cache_creation_input_token_cost": 5.0001e-7, - "cache_read_input_token_cost": 5.0001e-7, - "deprecation_date": "2024-08-30", - "input_cost_per_token": 5.0001e-7, - "input_dbu_cost_per_token": 0.000007143, - "litellm_provider": "databricks", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "mode": "chat", - "output_cost_per_token": 0, - "output_dbu_cost_per_token": 0, - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "supports_tool_choice": true - }, "databricks/databricks-qwen3-next-80b-a3b-instruct": { "cache_creation_input_token_cost": 1.5001e-7, "cache_read_input_token_cost": 1.5001e-7, @@ -14874,7 +16915,7 @@ "input_cost_per_token": 0.000004, "input_cost_per_token_above_272k_tokens": 0.000008, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -14945,6 +16986,8 @@ "supports_parallel_function_calling": true }, "deep-research-pro-preview-12-2025": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_batches": 1e-7, "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, @@ -14957,7 +17000,7 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -15927,18 +17970,6 @@ "supports_vision": false, "source": "https://deepinfra.com/pricing" }, - "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 4e-7, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_function_calling": true - }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, "max_input_tokens": 1000000, @@ -15949,7 +17980,11 @@ "mode": "chat", "supports_tool_choice": true, "supports_function_calling": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { "max_tokens": 1000000, @@ -15960,7 +17995,11 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true }, "deepinfra/google/gemini-3.1-flash-lite": { "max_tokens": 1000000, @@ -15974,7 +18013,8 @@ "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true }, "deepinfra/google/gemini-3.1-pro": { "max_tokens": 1000000, @@ -15988,7 +18028,8 @@ "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true }, "deepinfra/google/gemini-3.5-flash": { "max_tokens": 1000000, @@ -16002,7 +18043,8 @@ "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { "max_tokens": 1000000, @@ -16016,7 +18058,8 @@ "supports_response_schema": true, "supports_reasoning": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "source": "https://deepinfra.com/pricing", + "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { "max_tokens": 131072, @@ -16796,6 +18839,60 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "deepseek-flash": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "input_cost_per_token_cache_hit": 6e-9, + "litellm_provider": "deepseek", + "max_input_tokens": 1000000, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 0.0000012, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, @@ -16834,15 +18931,43 @@ }, "deepseek-v4-flash": { "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.4e-8, - "input_cost_per_token": 4.4e-7, - "input_cost_per_token_cache_hit": 1.4e-8, + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "input_cost_per_token_cache_hit": 6e-9, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.00000132, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 0.0000012, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -16856,19 +18981,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.4e-8, - "input_cost_per_token": 4.4e-7, - "input_cost_per_token_cache_hit": 1.4e-8, + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "input_cost_per_token_cache_hit": 6e-9, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.00000132, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 0.0000012, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -16894,6 +19047,34 @@ "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-8, + "input_cost_per_token": 6.6e-7, + "output_cost_per_token": 0.00000198, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, "output_cost_per_token": 0.00000396, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ @@ -16926,16 +19107,19 @@ "deepseek.v3.2": { "input_cost_per_token": 6.2e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 164000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.00000185, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0, @@ -16962,6 +19146,7 @@ "supports_tool_choice": true }, "deepseek/deepseek-coder": { + "cache_read_input_token_cost": 1.4e-8, "input_cost_per_token": 1.4e-7, "input_cost_per_token_cache_hit": 1.4e-8, "litellm_provider": "deepseek", @@ -16985,6 +19170,34 @@ "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, "output_cost_per_token": 0.0000012, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ @@ -17002,6 +19215,7 @@ "supports_vision": true }, "deepseek/deepseek-r1": { + "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 5.5e-7, "input_cost_per_token_cache_hit": 1.4e-7, "litellm_provider": "deepseek", @@ -17057,6 +19271,7 @@ "supports_tool_choice": true }, "deepseek/deepseek-v3.2": { + "cache_read_input_token_cost": 2.8e-8, "input_cost_per_token": 2.8e-7, "input_cost_per_token_cache_hit": 2.8e-8, "litellm_provider": "deepseek", @@ -17073,15 +19288,43 @@ }, "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.4e-8, - "input_cost_per_token": 4.4e-7, - "input_cost_per_token_cache_hit": 1.4e-8, + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "input_cost_per_token_cache_hit": 6e-9, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.00000132, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 0.0000012, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -17095,19 +19338,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "deepseek/deepseek-v4-flash-vision-exp": { "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1.4e-8, - "input_cost_per_token": 4.4e-7, - "input_cost_per_token_cache_hit": 1.4e-8, + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "input_cost_per_token_cache_hit": 6e-9, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.00000132, + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-9, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 0.0000012, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -17133,6 +19404,34 @@ "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-8, + "input_cost_per_token": 6.6e-7, + "output_cost_per_token": 0.00000198, + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, "output_cost_per_token": 0.00000396, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ @@ -17214,6 +19513,7 @@ "supports_vision": true }, "eu.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.95e-8, "input_cost_per_token": 7.8e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -17229,6 +19529,7 @@ "supports_tool_choice": true }, "eu.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 1.15e-8, "input_cost_per_token": 4.6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -17242,6 +19543,7 @@ "supports_tool_choice": true }, "eu.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2.625e-7, "input_cost_per_token": 0.00000105, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -17330,23 +19632,6 @@ "cache_read_input_token_cost": 3e-7, "cache_creation_input_token_cost": 0.00000375 }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-8, - "cache_creation_input_token_cost": 3.125e-7 - }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 0.000015, "litellm_provider": "bedrock", @@ -17362,23 +19647,6 @@ "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875 }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 - }, "eu.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 0.00001375, "cache_creation_input_token_cost_above_1hr": 0.000022, @@ -17648,6 +19916,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -17685,6 +19954,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -17712,6 +19982,46 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, + "eu.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_1hr": 0.0000088, + "cache_read_input_token_cost": 2.2e-7, + "input_cost_per_token": 0.0000044, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000022, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "eu.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 0.00000375, "cache_read_input_token_cost": 3e-7, @@ -17822,6 +20132,7 @@ "cache_read_input_token_cost": 2.2e-7, "input_cost_per_token": 0.0000022, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -17905,6 +20216,18 @@ "mode": "chat", "supports_video_input": true }, + "fal_ai/fal-ai/moondream3-preview/query": { + "input_cost_per_token": 4e-7, + "litellm_provider": "fal_ai", + "mode": "chat", + "output_cost_per_token": 0.0000035, + "source": "https://fal.ai/models/fal-ai/moondream3-preview/query", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_reasoning": true, + "supports_vision": true + }, "featherless_ai/featherless-ai/Qwerky-72B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, @@ -18410,14 +20733,17 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-9, + "cache_read_input_token_cost_priority": 8.75e-9, "input_cost_per_token": 2.2e-7, + "input_cost_per_token_priority": 2.75e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 8.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18432,42 +20758,50 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-7, - "input_cost_per_token": 0.00000174, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-8, + "cache_read_input_token_cost_priority": 5.5e-8, + "input_cost_per_token": 0.00000132, + "input_cost_per_token_priority": 0.00000165, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000348, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 0.00000396, + "output_cost_per_token_priority": 0.00000495, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { - "cache_read_input_token_cost": 4.4e-8, - "input_cost_per_token": 0.00000132, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { + "cache_read_input_token_cost": 7e-9, + "cache_read_input_token_cost_priority": 8.75e-9, + "input_cost_per_token": 2.2e-7, + "input_cost_per_token_priority": 2.75e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.00000396, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_priority": 8.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { "max_tokens": 131072, @@ -18738,14 +21072,17 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p2": { "cache_read_input_token_cost": 1.4e-7, + "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token": 0.0000014, + "input_cost_per_token_priority": 0.00000175, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.0000055, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18754,14 +21091,17 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p3": { "cache_read_input_token_cost": 2.6e-7, + "cache_read_input_token_cost_priority": 3.25e-7, "input_cost_per_token": 0.0000014, + "input_cost_per_token_priority": 0.00000175, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.0000055, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18770,13 +21110,16 @@ }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_priority": 3.75e-8, "input_cost_per_token": 1.5e-7, + "input_cost_per_token_priority": 1.875e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 6.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -18784,14 +21127,17 @@ }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-8, + "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_token": 1.5e-7, + "input_cost_per_token_priority": 1.8e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 7.2e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18965,14 +21311,17 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-7, + "cache_read_input_token_cost_priority": 2.2e-7, "input_cost_per_token": 9.5e-7, + "input_cost_per_token_priority": 0.0000015, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000006, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18981,14 +21330,17 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-7, + "cache_read_input_token_cost_priority": 2.85e-7, "input_cost_per_token": 9.5e-7, + "input_cost_per_token_priority": 0.000001425, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000006, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -18997,19 +21349,22 @@ }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_priority": 3.75e-7, "input_cost_per_token": 0.000003, + "input_cost_per_token_priority": 0.00000375, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, + "output_cost_per_token_priority": 0.00001875, "reasoning_effort_levels": [ "low", "high", "max" ], - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -19349,37 +21704,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/accounts/fireworks/models/minimax-m2p7": { - "cache_read_input_token_cost": 6e-8, - "input_cost_per_token": 3e-7, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://docs.fireworks.ai/serverless/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-8, + "cache_read_input_token_cost_priority": 9e-8, "input_cost_per_token": 3e-7, + "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 0.0000012, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.0000018, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { "max_tokens": 256000, @@ -19556,7 +21898,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000015, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -19581,7 +21923,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000024, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20380,7 +22722,7 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000016, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20389,12 +22731,15 @@ }, "fireworks_ai/accounts/fireworks/models/qwen3p8-max": { "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_priority": 3.75e-7, "input_cost_per_token": 0.000002, + "input_cost_per_token_priority": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000006, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000009, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20574,7 +22919,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000066, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20597,6 +22942,21 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-7, + "input_cost_per_token": 0.0000021, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.0000066, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000002, @@ -20643,7 +23003,7 @@ "high", "max" ], - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20689,14 +23049,17 @@ }, "fireworks_ai/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 7e-9, + "cache_read_input_token_cost_priority": 8.75e-9, "input_cost_per_token": 2.2e-7, + "input_cost_per_token_priority": 2.75e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 8.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20711,27 +23074,51 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, - "fireworks_ai/deepseek-v4-pro": { - "cache_read_input_token_cost": 1.45e-7, - "input_cost_per_token": 0.00000174, + "fireworks_ai/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-8, + "cache_read_input_token_cost_priority": 5.5e-8, + "input_cost_per_token": 0.00000132, + "input_cost_per_token_priority": 0.00000165, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000348, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 0.00000396, + "output_cost_per_token_priority": 0.00000495, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/deepseek-v4p1-flash": { + "cache_read_input_token_cost": 7e-9, + "cache_read_input_token_cost_priority": 8.75e-9, + "input_cost_per_token": 2.2e-7, + "input_cost_per_token_priority": 2.75e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_priority": 8.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 6e-7, @@ -20781,14 +23168,17 @@ }, "fireworks_ai/glm-5p2": { "cache_read_input_token_cost": 1.4e-7, + "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token": 0.0000014, + "input_cost_per_token_priority": 0.00000175, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.0000055, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20827,16 +23217,70 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/glm-5p3": { + "cache_read_input_token_cost": 2.6e-7, + "cache_read_input_token_cost_priority": 3.25e-7, + "input_cost_per_token": 0.0000014, + "input_cost_per_token_priority": 0.00000175, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "output_cost_per_token_priority": 0.0000055, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-7, + "input_cost_per_token": 0.0000021, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.0000066, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-flash": { + "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_priority": 3.75e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_priority": 1.875e-7, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-7, + "output_cost_per_token_priority": 6.25e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-8, + "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_token": 1.5e-7, + "input_cost_per_token_priority": 1.8e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-7, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 7.2e-7, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20875,14 +23319,17 @@ }, "fireworks_ai/kimi-k2p6": { "cache_read_input_token_cost": 1.6e-7, + "cache_read_input_token_cost_priority": 2.2e-7, "input_cost_per_token": 9.5e-7, + "input_cost_per_token_priority": 0.0000015, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000006, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20907,14 +23354,17 @@ }, "fireworks_ai/kimi-k2p7-code": { "cache_read_input_token_cost": 1.9e-7, + "cache_read_input_token_cost_priority": 2.85e-7, "input_cost_per_token": 9.5e-7, + "input_cost_per_token_priority": 0.000001425, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.000004, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000006, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -20939,19 +23389,22 @@ }, "fireworks_ai/kimi-k3": { "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_priority": 3.75e-7, "input_cost_per_token": 0.000003, + "input_cost_per_token_priority": 0.00000375, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.000015, + "output_cost_per_token_priority": 0.00001875, "reasoning_effort_levels": [ "low", "high", "max" ], - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -21014,37 +23467,24 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "fireworks_ai/minimax-m2p7": { - "cache_read_input_token_cost": 6e-8, - "input_cost_per_token": 3e-7, - "litellm_provider": "fireworks_ai", - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "max_tokens": 196608, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://docs.fireworks.ai/serverless/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false - }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-8, + "cache_read_input_token_cost_priority": 9e-8, "input_cost_per_token": 3e-7, + "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 0.0000012, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.0000018, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-8, @@ -21055,7 +23495,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.0000015, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -21071,7 +23511,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0000024, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -21103,7 +23543,7 @@ "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0000016, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -21112,100 +23552,198 @@ }, "fireworks_ai/qwen3p8-max": { "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_priority": 3.75e-7, "input_cost_per_token": 0.000002, + "input_cost_per_token_priority": 0.000003, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.000006, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 0.000009, + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "friendliai/meta-llama-3.1-70b-instruct": { - "input_cost_per_token": 6e-7, + "friendliai/MiniMaxAI/MiniMax-M2.5": { "litellm_provider": "friendliai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-7, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "max_tokens": 196608, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 6e-8, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", + "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/meta-llama-3.1-8b-instruct": { - "input_cost_per_token": 1e-7, + "friendliai/deepseek-ai/DeepSeek-V3.2": { "litellm_provider": "friendliai", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.0000015, + "cache_read_input_token_cost": 2.5e-7, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, "mode": "chat", - "output_cost_per_token": 1e-7, + "comment": "DeepSeek chat model for instruction following, coding, and analysis", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/google/gemma-4-31B-it": { + "litellm_provider": "friendliai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 4e-7, + "supports_prompt_caching": false, + "supports_reasoning": true, + "reasoning_effort_levels": [], "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, + "supports_native_structured_output": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_image_input": true, + "supports_video_input": false, + "mode": "chat", + "comment": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", + "source": "https://api.friendli.ai/serverless/v1/models" }, - "friendliai/zai-org/GLM-5.3": { + "friendliai/zai-org/GLM-5.1": { "litellm_provider": "friendliai", + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "max_tokens": 202752, + "input_cost_per_token": 0.0000014, + "output_cost_per_token": 0.0000044, + "cache_read_input_token_cost": 2.6e-7, + "supports_prompt_caching": true, "supports_reasoning": true, + "reasoning_effort_levels": [], "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/zai-org/GLM-5.2": { + "litellm_provider": "friendliai", "max_input_tokens": 1048576, + "max_output_tokens": 1048576, "max_tokens": 1048576, + "input_cost_per_token": 0.0000014, + "output_cost_per_token": 0.0000044, + "cache_read_input_token_cost": 2.6e-7, + "supports_prompt_caching": true, + "supports_reasoning": true, + "reasoning_effort_levels": [ + "high", + "max" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_native_structured_output": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, + "mode": "chat", + "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", + "source": "https://api.friendli.ai/serverless/v1/models" + }, + "friendliai/zai-org/GLM-5.3": { + "litellm_provider": "friendliai", + "max_input_tokens": 1048576, "max_output_tokens": 1048576, + "max_tokens": 1048576, "input_cost_per_token": 0.00000126, "output_cost_per_token": 0.00000396, "cache_read_input_token_cost": 2.34e-7, "supports_prompt_caching": true, + "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], + "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": false, + "supports_image_input": false, + "supports_video_input": false, "mode": "chat", "comment": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", - "source": "https://api.friendli.ai/serverless/v1/models", - "supports_vision": false, - "supports_image_input": false + "source": "https://api.friendli.ai/serverless/v1/models" }, "friendliai/zai-org/GLM-5.3-Flash": { "litellm_provider": "friendliai", - "supports_reasoning": true, - "supports_function_calling": true, "max_input_tokens": 1048576, - "max_tokens": 1048576, "max_output_tokens": 1048576, + "max_tokens": 1048576, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "cache_read_input_token_cost": 3e-8, "supports_prompt_caching": true, + "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], + "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "mode": "chat", - "comment": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", - "source": "https://api.friendli.ai/serverless/v1/models", "supports_vision": true, "supports_image_input": true, - "supports_video_input": true + "supports_video_input": true, + "mode": "chat", + "comment": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", + "source": "https://api.friendli.ai/serverless/v1/models" }, "ft:gpt-3.5-turbo": { "deprecation_date": "2026-10-23", @@ -21218,6 +23756,7 @@ "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_batches": 0.000003, + "source": "https://developers.openai.com/api/docs/pricing", "supports_system_messages": true, "supports_tool_choice": true }, @@ -21273,6 +23812,7 @@ }, "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-7, + "cache_read_input_token_cost_batches": 5e-7, "input_cost_per_token": 0.000003, "input_cost_per_token_batches": 0.0000015, "litellm_provider": "openai", @@ -21282,6 +23822,7 @@ "mode": "chat", "output_cost_per_token": 0.000012, "output_cost_per_token_batches": 0.000006, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -21291,6 +23832,7 @@ }, "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_batches": 1e-7, "input_cost_per_token": 8e-7, "input_cost_per_token_batches": 4e-7, "litellm_provider": "openai", @@ -21300,6 +23842,7 @@ "mode": "chat", "output_cost_per_token": 0.0000032, "output_cost_per_token_batches": 0.0000016, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -21309,6 +23852,7 @@ }, "ft:gpt-4.1-nano-2025-04-14": { "cache_read_input_token_cost": 5e-8, + "cache_read_input_token_cost_batches": 2.5e-8, "deprecation_date": "2026-10-23", "input_cost_per_token": 2e-7, "input_cost_per_token_batches": 1e-7, @@ -21319,6 +23863,7 @@ "mode": "chat", "output_cost_per_token": 8e-7, "output_cost_per_token_batches": 4e-7, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -21328,15 +23873,17 @@ }, "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 0.000001875, + "cache_read_input_token_cost_batches": 9e-7, "input_cost_per_token": 0.00000375, - "input_cost_per_token_batches": 0.000001875, + "input_cost_per_token_batches": 0.000002225, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.000015, - "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_batches": 0.0000125, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21365,6 +23912,7 @@ }, "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-7, + "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_token": 3e-7, "input_cost_per_token_batches": 1.5e-7, "litellm_provider": "openai", @@ -21374,6 +23922,7 @@ "mode": "chat", "output_cost_per_token": 0.0000012, "output_cost_per_token_batches": 6e-7, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -21384,6 +23933,7 @@ }, "ft:o4-mini-2025-04-16": { "cache_read_input_token_cost": 0.000001, + "cache_read_input_token_cost_batches": 5e-7, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.000004, "input_cost_per_token_batches": 0.000002, @@ -21394,6 +23944,7 @@ "mode": "chat", "output_cost_per_token": 0.000016, "output_cost_per_token_batches": 0.000008, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -21401,152 +23952,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-001": { - "cache_read_input_token_cost": 3.75e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, @@ -21557,7 +23962,7 @@ "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -21572,8 +23977,11 @@ "supports_vision": true }, "gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-7, "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_flex": 3e-8, + "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "vertex_ai-language-models", @@ -21583,7 +23991,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21616,6 +24024,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-7, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, + "output_cost_per_token_priority": 0.0000045, "supports_image_size": false }, "gemini-2.5-flash-image": { @@ -21623,6 +24038,9 @@ "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -21632,8 +24050,10 @@ "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21664,8 +24084,11 @@ "supports_image_size": false }, "gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-8, "deprecation_date": "2026-10-20", "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_flex": 1e-8, + "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-language-models", @@ -21675,54 +24098,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21755,6 +24131,13 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-8, + "input_cost_per_token_batches": 5e-8, + "input_cost_per_token_flex": 5e-8, + "input_cost_per_token_priority": 1.8e-7, + "output_cost_per_token_batches": 2e-7, + "output_cost_per_token_flex": 2e-7, + "output_cost_per_token_priority": 7.2e-7, "supports_image_size": false }, "gemini-2.5-flash-lite-preview-09-2025": { @@ -21854,6 +24237,9 @@ "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-7, + "cache_read_input_token_cost_flex": 1.25e-7, + "cache_read_input_token_cost_priority": 2.25e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "vertex_ai-language-models", @@ -21863,7 +24249,7 @@ "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -21881,6 +24267,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, @@ -21893,19 +24280,29 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_above_200k_tokens_priority": 0.0000045, + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.00000225, + "output_cost_per_token_above_200k_tokens_priority": 0.000027, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.000018 }, "gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.000001, + "input_cost_per_token_batches": 5e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", + "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.00002, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], @@ -21928,7 +24325,9 @@ } }, "gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost": 5e-8, + "cache_read_input_token_cost_flex": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "litellm_provider": "vertex_ai-language-models", @@ -21938,7 +24337,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21976,13 +24375,28 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-7, + "input_cost_per_token_batches": 2.5e-7, + "input_cost_per_token_flex": 2.5e-7, + "output_cost_per_token_batches": 0.0000015, + "output_cost_per_token_flex": 0.0000015 }, "gemini-3-pro-image": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_batches": 1e-7, + "cache_read_input_token_cost_flex": 1e-7, + "cache_read_input_token_cost_priority": 3.6e-7, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_flex": 0.000001, + "input_cost_per_token_priority": 0.0000036, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -21991,8 +24405,12 @@ "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "output_cost_per_token_batches": 0.000006, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 0.000006, + "output_cost_per_token_priority": 0.0000216, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22059,23 +24477,26 @@ }, "web_search_billing_unit": "per_query" }, - "gemini-3-pro-preview": { - "deprecation_date": "2026-03-26", - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, + "gemini-3.1-flash-image": { + "cache_read_input_token_cost": 5e-8, + "cache_read_input_token_cost_batches": 2.5e-8, + "cache_read_input_token_cost_flex": 2.5e-8, + "deprecation_date": "2027-05-28", + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-7, + "input_cost_per_token_batches": 2.5e-7, + "input_cost_per_token_flex": 2.5e-7, "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 0.00006, + "output_cost_per_token": 0.000003, + "output_cost_per_token_batches": 0.0000015, + "output_cost_per_token_flex": 0.0000015, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22083,31 +24504,18 @@ ], "supported_modalities": [ "text", - "image", - "audio", - "video" + "image" ], "supported_output_modalities": [ - "text" + "text", + "image" ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, @@ -22115,46 +24523,7 @@ }, "web_search_billing_unit": "per_query" }, - "gemini-3.1-flash-image": { - "deprecation_date": "2027-05-28", - "input_cost_per_image": 0.00056, - "input_cost_per_token": 5e-7, - "litellm_provider": "vertex_ai-language-models", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.0672, - "output_cost_per_image_token": 0.00006, - "output_cost_per_token": 0.000003, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini-3.1-flash-image-preview": { + "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-7, "litellm_provider": "vertex_ai-language-models", @@ -22193,8 +24562,10 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-8, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, @@ -22212,7 +24583,7 @@ "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22248,13 +24619,17 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-7 }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, + "cache_read_input_token_cost_flex": 1.25e-8, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, + "input_cost_per_token_flex": 1.25e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -22264,6 +24639,7 @@ "output_cost_per_image_token": 0.00003, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, + "output_cost_per_token_flex": 7.5e-7, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -22354,7 +24730,7 @@ "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22388,13 +24764,16 @@ "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -22453,6 +24832,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-7, + "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_audio_token": 0.0000015, "input_cost_per_token": 0.0000015, "litellm_provider": "vertex_ai-language-models", @@ -22462,7 +24842,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22512,8 +24892,9 @@ "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_batches": 1.5e-8, "cache_read_input_token_cost_flex": 1.5e-8, - "cache_read_input_token_cost_priority": 5e-8, + "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_token": 3e-7, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, @@ -22528,7 +24909,7 @@ "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22569,6 +24950,7 @@ "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -22582,7 +24964,7 @@ "output_cost_per_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22626,6 +25008,7 @@ "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -22639,7 +25022,7 @@ "output_cost_per_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22661,6 +25044,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -22683,6 +25067,7 @@ "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -22696,7 +25081,7 @@ "output_cost_per_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22718,6 +25103,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -22784,18 +25170,17 @@ } }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, + "output_cost_per_reasoning_token": 0.00000375, + "output_cost_per_token": 0.00000375, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22824,25 +25209,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-8, + "cache_read_input_token_cost_priority": 1.35e-7, + "input_cost_per_token_batches": 3.75e-7, + "input_cost_per_token_flex": 3.75e-7, + "input_cost_per_token_priority": 0.00000135, + "output_cost_per_token_batches": 0.000001875, + "output_cost_per_token_flex": 0.000001875, + "output_cost_per_token_priority": 0.00000675, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22871,11 +25268,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-8, + "cache_read_input_token_cost_priority": 5e-8, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, + "output_cost_per_token_priority": 0.0000045, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 0.0000015, @@ -22888,7 +25297,7 @@ "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "output_cost_per_video_token": 0.0000175, - "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions" ], @@ -22909,22 +25318,23 @@ "supports_vision": true }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -22948,11 +25358,26 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_priority": 3.6e-7, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000036, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_token_priority": 0.0000216, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-7, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "gemini-robotics-er-1.5-preview": { "cache_read_input_token_cost": 0, @@ -23031,156 +25456,6 @@ "search_context_size_high": 0.035 } }, - "gemini/gemini-2.0-flash": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-7, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-001": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-7, - "rpm": 10000, - "source": "https://ai.google.dev/pricing#2_0flash", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 10000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-lite": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-7, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-2.0-flash-lite-001": { - "cache_read_input_token_cost": 1.875e-8, - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7.5e-8, - "input_cost_per_token": 7.5e-8, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-7, - "rpm": 4000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 4000000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, @@ -23192,7 +25467,7 @@ "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/computer-use", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -23212,18 +25487,22 @@ "tpm": 800000 }, "gemini/gemini-2.5-flash": { + "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_batches": 3e-8, + "cache_read_input_token_cost_flex": 3e-8, + "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23257,6 +25536,14 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 5e-7, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, + "output_cost_per_token_priority": 0.0000045, + "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-2.5-flash-image": { @@ -23264,9 +25551,12 @@ "deprecation_date": "2026-10-02", "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, "litellm_provider": "gemini", "supports_reasoning": false, - "max_input_tokens": 32768, + "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", @@ -23275,7 +25565,7 @@ "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23292,183 +25582,41 @@ "image" ], "supports_audio_output": false, - "supports_function_calling": true, + "supports_function_calling": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, + "supports_web_search": false, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "supports_audio_input": false, "supports_image_size": false }, "gemini/gemini-2.5-flash-lite": { + "cache_read_input_audio_token_cost": 3e-8, "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_batches": 1e-8, + "cache_read_input_token_cost_flex": 1e-8, + "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_audio_token": 3e-7, "input_cost_per_token": 1e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-lite-preview-09-2025": { - "cache_read_input_token_cost": 1e-8, - "deprecation_date": "2026-03-31", - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-7, "output_cost_per_token": 4e-7, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025, - "supports_image_size": false - }, - "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 3e-8, - "deprecation_date": "2026-02-17", - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, - "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -23503,26 +25651,38 @@ "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_audio_token_batches": 1.5e-7, + "input_cost_per_token_batches": 5e-8, + "input_cost_per_token_flex": 5e-8, + "input_cost_per_token_priority": 1.8e-7, + "output_cost_per_token_batches": 2e-7, + "output_cost_per_token_flex": 2e-7, + "output_cost_per_token_priority": 7.2e-7, + "supports_audio_input": true, "supports_image_size": false }, "gemini/gemini-2.5-pro": { "cache_read_input_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-7, + "cache_read_input_token_cost_batches": 1.25e-7, + "cache_read_input_token_cost_flex": 1.25e-7, + "cache_read_input_token_cost_priority": 2.25e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, - "input_cost_per_token_priority": 0.00000125, - "input_cost_per_token_above_200k_tokens_priority": 0.0000025, + "input_cost_per_token_priority": 0.00000225, + "input_cost_per_token_above_200k_tokens_priority": 0.0000045, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_above_200k_tokens": 0.000015, - "output_cost_per_token_priority": 0.00001, - "output_cost_per_token_above_200k_tokens_priority": 0.000015, + "output_cost_per_token_priority": 0.000018, + "output_cost_per_token_above_200k_tokens_priority": 0.000027, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -23540,6 +25700,7 @@ "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, @@ -23553,17 +25714,23 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.025, + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_flex": 6.25e-7, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_flex": 0.000005 }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token": 0.000001, + "input_cost_per_token_batches": 5e-7, "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_audio_token": 0.00002, "output_cost_per_token": 0.00002, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -23574,28 +25741,32 @@ "audio" ], "supports_audio_output": false, - "supports_function_calling": true, + "supports_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, + "supports_vision": false, + "supports_web_search": false, "tpm": 10000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_audio_input": false }, "gemini/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost": 5e-8, + "cache_read_input_token_cost_batches": 5e-8, + "cache_read_input_token_cost_flex": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 5e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 0.000003, "output_cost_per_token": 0.000003, @@ -23639,12 +25810,20 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-7, + "input_cost_per_token_batches": 2.5e-7, + "input_cost_per_token_flex": 2.5e-7, + "output_cost_per_token_batches": 0.0000015, + "output_cost_per_token_flex": 0.0000015, + "supports_audio_input": true }, "gemini/gemini-3-pro-image": { "input_cost_per_image": 0.0011, "input_cost_per_token": 0.000002, "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_flex": 0.000001, + "input_cost_per_token_priority": 0.0000036, "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -23656,7 +25835,9 @@ "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", + "output_cost_per_token_flex": 0.000006, + "output_cost_per_token_priority": 0.0000216, + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23672,7 +25853,7 @@ ], "supports_function_calling": false, "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, @@ -23684,154 +25865,11 @@ "web_search_billing_unit": "per_query", "supports_reasoning": false }, - "gemini/gemini-3-pro-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_image": 0.0011, - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, - "output_cost_per_token": 0.000012, - "rpm": 1000, - "tpm": 4000000, - "output_cost_per_token_batches": 0.000006, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3-pro-preview": { - "deprecation_date": "2026-03-09", - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "input_cost_per_token_priority": 0.0000036, - "input_cost_per_token_above_200k_tokens_priority": 0.0000072, - "output_cost_per_token_priority": 0.0000216, - "output_cost_per_token_above_200k_tokens_priority": 0.0000324, - "cache_read_input_token_cost_priority": 3.6e-7, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, "gemini/gemini-3.1-flash-image": { "input_cost_per_token": 5e-7, "input_cost_per_token_batches": 2.5e-7, "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.045, - "output_cost_per_image_token": 0.00006, - "output_cost_per_token": 0.000003, - "output_cost_per_token_batches": 0.0000015, - "rpm": 1000, - "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_vision": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query" - }, - "gemini/gemini-3.1-flash-image-preview": { - "deprecation_date": "2026-06-25", - "input_cost_per_token": 5e-7, - "input_cost_per_token_batches": 2.5e-7, - "litellm_provider": "gemini", - "max_input_tokens": 65536, + "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "image_generation", @@ -23841,7 +25879,7 @@ "output_cost_per_token_batches": 0.0000015, "rpm": 1000, "tpm": 4000000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23858,7 +25896,7 @@ "supports_function_calling": false, "supports_prompt_caching": true, "supports_reasoning": false, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, @@ -23870,7 +25908,9 @@ "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-8, "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "deprecation_date": "2027-05-07", @@ -23890,7 +25930,7 @@ "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23927,7 +25967,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-7 }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, @@ -23943,7 +25984,7 @@ "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "rpm": 1000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-image", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -23957,66 +25998,15 @@ "text", "image" ], - "supports_function_calling": true, + "supports_function_calling": false, "supports_prompt_caching": false, "supports_reasoning": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, + "supports_web_search": false, "tpm": 4000000 }, - "gemini/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-8, - "deprecation_date": "2026-05-25", - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "supports_native_streaming": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 - }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 2e-7, @@ -24033,7 +26023,7 @@ "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -24068,13 +26058,17 @@ "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_batches": 2e-7, + "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -24092,7 +26086,7 @@ "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -24127,23 +26121,28 @@ "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_batches": 2e-7, + "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "gemini/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 1.5e-7, + "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_audio_token": 0.0000015, "input_cost_per_token": 0.0000015, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, @@ -24198,6 +26197,7 @@ }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_batches": 2e-8, "cache_read_input_token_cost_flex": 2e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token": 3e-7, @@ -24257,6 +26257,7 @@ "gemini/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -24316,6 +26317,7 @@ "gemini/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -24352,6 +26354,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -24375,6 +26378,7 @@ "gemini/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -24411,6 +26415,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -24478,16 +26483,15 @@ "tpm": 4000000 }, "gemini/gemini-flash-latest": { - "cache_read_input_token_cost": 3e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 3e-7, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000025, - "output_cost_per_token": 0.0000025, + "output_cost_per_reasoning_token": 0.00000375, + "output_cost_per_token": 0.00000375, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ @@ -24518,23 +26522,35 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-8, + "cache_read_input_token_cost_priority": 1.35e-7, + "input_cost_per_token_batches": 3.75e-7, + "input_cost_per_token_flex": 3.75e-7, + "input_cost_per_token_priority": 0.00000135, + "output_cost_per_token_batches": 0.000001875, + "output_cost_per_token_flex": 0.000001875, + "output_cost_per_token_priority": 0.00000675, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 3e-7, - "input_cost_per_token": 1e-7, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 3e-7, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-7, - "output_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ @@ -24565,11 +26581,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-8, + "cache_read_input_token_cost_priority": 5e-8, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, + "output_cost_per_token_priority": 0.0000045, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-gemma-2-27b-it": { "input_cost_per_token": 3.5e-7, @@ -24603,7 +26631,7 @@ "input_cost_per_audio_token": 0.0000015, "input_cost_per_token": 0.0000015, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -24667,22 +26695,23 @@ "deprecation_date": "2026-09-30" }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_above_200k_tokens": 0.000015, + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -24705,122 +26734,48 @@ "supports_vision": true, "supports_web_search": true, "tpm": 800000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025 - }, - "gemini/gemini-robotics-er-1.5-preview": { - "cache_read_input_token_cost": 0, - "deprecation_date": "2026-04-30", - "input_cost_per_token": 3e-7, - "input_cost_per_audio_token": 0.000001, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "output_cost_per_reasoning_token": 0.0000025, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "video", - "audio" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "rpm": 10, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } - }, - "gemini/gemini-robotics-er-1.6-preview": { - "deprecation_date": "2026-08-31", - "input_cost_per_audio_token": 0.000002, - "input_cost_per_token": 0.000001, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 0.000005, - "output_cost_per_token": 0.000005, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_priority": 3.6e-7, + "input_cost_per_token_above_200k_tokens_priority": 0.0000072, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000036, + "output_cost_per_token_above_200k_tokens_priority": 0.0000324, + "output_cost_per_token_batches": 0.000006, + "output_cost_per_token_priority": 0.0000216, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-7, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "gemini/gemini-robotics-er-2-preview": { - "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_batches": 5e-8, "input_cost_per_audio_token": 0.000002, - "input_cost_per_token": 0.000002, + "input_cost_per_token": 0.000001, + "input_cost_per_token_batches": 5e-7, "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 0.00001, - "output_cost_per_token": 0.00001, + "output_cost_per_token": 0.000005, + "output_cost_per_token_batches": 0.0000025, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -25375,26 +27330,6 @@ "supports_parallel_function_calling": true, "supports_vision": true }, - "github_copilot/gemini-2.5-pro": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, - "github_copilot/gemini-3-pro-preview": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, "github_copilot/gemini-3.5-flash": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, @@ -25757,6 +27692,38 @@ "supports_response_schema": true, "supports_vision": true }, + "github_copilot/gpt-6-luna": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "source": "https://docs.github.com/en/copilot/reference/ai-models/supported-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-sol": { + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "source": "https://docs.github.com/en/copilot/reference/ai-models/supported-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, "github_copilot/grok-4.5": { "litellm_provider": "github_copilot", "max_input_tokens": 128000, @@ -25926,7 +27893,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 0.0000125, @@ -25964,7 +27932,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 0.00000125, @@ -26096,7 +28065,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -26107,6 +28077,7 @@ "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -26133,7 +28104,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -26144,6 +28116,7 @@ "cache_read_input_token_cost": 5e-7, "input_cost_per_token": 0.000005, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -26169,7 +28142,48 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00002, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "thinking_always_on": true, + "supports_forced_tool_use": false }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 0.00000375, @@ -26272,7 +28286,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -26281,6 +28296,7 @@ "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -26309,7 +28325,28 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "global.openai.gpt-5.6-luna": { "input_cost_per_token": 2e-7, @@ -26333,8 +28370,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "global.openai.gpt-5.6-sol": { @@ -26359,8 +28399,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "global.openai.gpt-5.6-terra": { @@ -26385,8 +28428,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "global.openai.gpt-6-astra": { @@ -26411,9 +28457,13 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" }, @@ -26533,18 +28583,8 @@ "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, - "supports_vision": true - }, - "gmi/google/gemini-3-pro-preview": { - "input_cost_per_token": 0.000002, - "litellm_provider": "gmi", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 0.000012, - "supports_function_calling": true, - "supports_vision": true + "supports_vision": true, + "supports_system_messages": true }, "gmi/moonshotai/Kimi-K2-Thinking": { "input_cost_per_token": 8e-7, @@ -26620,10 +28660,14 @@ "input_cost_per_token": 9e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, @@ -26631,10 +28675,14 @@ "input_cost_per_token": 2.3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, @@ -26642,10 +28690,13 @@ "input_cost_per_token": 4e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-8, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true }, @@ -26658,6 +28709,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, @@ -26666,12 +28718,15 @@ "gpt-3.5-turbo-0125": { "deprecation_date": "2026-10-23", "input_cost_per_token": 5e-7, + "input_cost_per_token_batches": 2.5e-7, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0000015, + "output_cost_per_token_batches": 7.5e-7, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -26681,12 +28736,15 @@ "gpt-3.5-turbo-1106": { "deprecation_date": "2026-09-28", "input_cost_per_token": 0.000001, + "input_cost_per_token_batches": 0.000001, "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000002, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -26720,42 +28778,18 @@ "supports_system_messages": true, "supports_tool_choice": true }, - "gpt-4-0125-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 0.00003, - "litellm_provider": "openai", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00006, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4-0613": { "deprecation_date": "2026-10-23", "input_cost_per_token": 0.00003, + "input_cost_per_token_batches": 0.000015, "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00006, + "output_cost_per_token_batches": 0.00003, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_system_messages": true, @@ -26796,12 +28830,15 @@ "gpt-4-turbo-2024-04-09": { "deprecation_date": "2026-10-23", "input_cost_per_token": 0.00001, + "input_cost_per_token_batches": 0.000005, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00003, + "output_cost_per_token_batches": 0.000015, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -26810,22 +28847,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4-turbo-preview": { - "deprecation_date": "2026-03-26", - "input_cost_per_token": 0.00001, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00003, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4.1": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_priority": 8.75e-7, @@ -26845,6 +28866,7 @@ "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -26887,6 +28909,7 @@ "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -26929,6 +28952,7 @@ "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -26971,6 +28995,7 @@ "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27009,6 +29034,7 @@ "output_cost_per_token": 4e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27046,6 +29072,7 @@ "output_cost_per_token": 4e-7, "output_cost_per_token_priority": 8e-7, "output_cost_per_token_batches": 2e-7, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27082,6 +29109,7 @@ "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_priority": 0.000017, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27104,6 +29132,7 @@ "output_cost_per_token": 0.000015, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00002625, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27126,6 +29155,7 @@ "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.000017, "output_cost_per_token_batches": 0.000005, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27149,6 +29179,7 @@ "output_cost_per_token": 0.00001, "output_cost_per_token_priority": 0.000017, "output_cost_per_token_batches": 0.000005, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27158,24 +29189,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 0.00004, - "input_cost_per_token": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00008, - "output_cost_per_token": 0.00001, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 0.00004, @@ -27238,7 +29251,8 @@ "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 - } + }, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-8, @@ -27259,6 +29273,7 @@ "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27268,24 +29283,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "gpt-4o-mini-audio-preview": { - "deprecation_date": "2026-05-07", - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 6e-7, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, "gpt-4o-mini-audio-preview-2024-12-17": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 0.00001, @@ -27330,32 +29327,6 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-mini-search-preview-2025-03-11": { - "cache_read_input_token_cost": 7.5e-8, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 1.5e-7, - "input_cost_per_token_batches": 7.5e-8, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 6e-7, - "output_cost_per_token_batches": 3e-7, - "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 - }, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 0.00000125, "input_cost_per_token": 0.0000025, @@ -27382,37 +29353,65 @@ "supports_vision": true, "supports_web_search": true }, - "gpt-4o-search-preview-2025-03-11": { - "cache_read_input_token_cost": 0.00000125, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.0000025, - "input_cost_per_token_batches": 0.00000125, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_flex": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { - "search_context_size_high": 0.025, - "search_context_size_low": 0.025, - "search_context_size_medium": 0.025 + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_minimal_reasoning_effort": true }, - "gpt-5": { + "gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, + "deprecation_date": "2026-12-11", "input_cost_per_token": 0.00000125, + "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", @@ -27421,6 +29420,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { @@ -27428,54 +29428,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5-2025-08-07": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_flex": 6.25e-8, - "cache_read_input_token_cost_priority": 2.5e-7, - "deprecation_date": "2026-12-11", - "input_cost_per_token": 0.00000125, - "input_cost_per_token_flex": 6.25e-7, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_flex": 0.000005, - "output_cost_per_token_priority": 0.00002, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27538,47 +29491,13 @@ "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true }, - "gpt-5-chat-latest": { - "cache_read_input_token_cost": 1.25e-7, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.00000125, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, "gpt-5-mini": { "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token": 2.5e-7, + "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "openai", @@ -27587,6 +29506,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000001, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { @@ -27594,6 +29514,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27623,10 +29544,12 @@ }, "gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "deprecation_date": "2026-12-11", "input_cost_per_token": 2.5e-7, + "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "litellm_provider": "openai", @@ -27635,6 +29558,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000001, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { @@ -27642,6 +29566,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27671,8 +29596,10 @@ }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_batches": 2.5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token": 5e-8, + "input_cost_per_token_batches": 2.5e-8, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "litellm_provider": "openai", @@ -27681,12 +29608,14 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27716,9 +29645,11 @@ }, "gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_batches": 2.5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "deprecation_date": "2026-12-11", "input_cost_per_token": 5e-8, + "input_cost_per_token_batches": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "input_cost_per_token_flex": 2.5e-8, "litellm_provider": "openai", @@ -27727,12 +29658,14 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -27774,6 +29707,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27801,6 +29735,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -27815,6 +29750,8 @@ }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, @@ -27855,11 +29792,18 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_flex": 6.25e-7, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_flex": 0.000005, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_batches": 6.25e-8, + "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token": 0.00000125, "input_cost_per_token_priority": 0.0000025, @@ -27900,57 +29844,18 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-7, + "input_cost_per_token_flex": 6.25e-7, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_flex": 0.000005, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true - }, - "gpt-5.1-chat-latest": { - "cache_read_input_token_cost": 1.25e-7, - "cache_read_input_token_cost_priority": 2.5e-7, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.00000125, - "input_cost_per_token_priority": 0.0000025, - "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "output_cost_per_token_priority": 0.00002, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_function_calling": false, - "supports_native_streaming": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_batches": 8.75e-8, + "cache_read_input_token_cost_flex": 8.75e-8, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, @@ -27992,11 +29897,18 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 8.75e-7, + "input_cost_per_token_flex": 8.75e-7, + "output_cost_per_token_batches": 0.000007, + "output_cost_per_token_flex": 0.000007, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-7, + "cache_read_input_token_cost_batches": 8.75e-8, + "cache_read_input_token_cost_flex": 8.75e-8, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token": 0.00000175, "input_cost_per_token_priority": 0.0000035, @@ -28038,29 +29950,43 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 8.75e-7, + "input_cost_per_token_flex": 8.75e-7, + "output_cost_per_token_batches": 0.000007, + "output_cost_per_token_flex": 0.000007, + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": false }, - "gpt-5.2-chat-latest": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, + "gpt-5.4": { + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "cache_read_input_token_cost_batches": 1.3e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-7, + "cache_read_input_token_cost_flex": 1.3e-7, + "cache_read_input_token_cost_priority": 5e-7, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_above_272k_tokens": 0.000005, + "input_cost_per_token_flex": 0.00000125, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_above_272k_tokens_batches": 0.0000025, + "input_cost_per_token_priority": 0.000005, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_272k_tokens": 0.0000225, + "output_cost_per_token_flex": 0.0000075, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_above_272k_tokens_batches": 0.00001125, + "output_cost_per_token_priority": 0.00003, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -28080,31 +30006,44 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 0.0000025, + "output_cost_per_token_above_272k_tokens_flex": 0.00001125, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, + "source": "https://developers.openai.com/api/docs/pricing" }, - "gpt-5.3-chat-latest": { - "cache_read_input_token_cost": 1.75e-7, - "cache_read_input_token_cost_priority": 3.5e-7, - "deprecation_date": "2026-08-10", - "input_cost_per_token": 0.00000175, - "input_cost_per_token_priority": 0.0000035, + "gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "cache_read_input_token_cost_batches": 1.3e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-7, + "cache_read_input_token_cost_flex": 1.3e-7, + "cache_read_input_token_cost_priority": 5e-7, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_above_272k_tokens": 0.000005, + "input_cost_per_token_flex": 0.00000125, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_above_272k_tokens_batches": 0.0000025, + "input_cost_per_token_priority": 0.000005, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000014, - "output_cost_per_token_priority": 0.000028, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_272k_tokens": 0.0000225, + "output_cost_per_token_flex": 0.0000075, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_above_272k_tokens_batches": 0.00001125, + "output_cost_per_token_priority": 0.00003, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", + "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -28124,139 +30063,40 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "input_cost_per_token_above_272k_tokens_flex": 0.0000025, + "output_cost_per_token_above_272k_tokens_flex": 0.00001125, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, + "source": "https://developers.openai.com/api/docs/pricing" }, - "gpt-5.4": { - "cache_read_input_token_cost": 2.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 5e-7, - "cache_read_input_token_cost_flex": 1.3e-7, - "cache_read_input_token_cost_priority": 5e-7, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_above_272k_tokens": 0.000005, - "input_cost_per_token_flex": 0.00000125, - "input_cost_per_token_batches": 0.00000125, - "input_cost_per_token_priority": 0.000005, + "gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, + "cache_read_input_token_cost_flex": 3.75e-8, + "cache_read_input_token_cost_priority": 1.5e-7, + "input_cost_per_token": 7.5e-7, + "input_cost_per_token_flex": 3.75e-7, + "input_cost_per_token_batches": 3.75e-7, + "input_cost_per_token_priority": 0.0000015, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_272k_tokens": 0.0000225, - "output_cost_per_token_flex": 0.0000075, - "output_cost_per_token_batches": 0.0000075, - "output_cost_per_token_priority": 0.00003, + "output_cost_per_token": 0.0000045, + "output_cost_per_token_flex": 0.00000225, + "output_cost_per_token_batches": 0.00000225, + "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true, - "input_cost_per_token_above_272k_tokens_flex": 0.0000025, - "output_cost_per_token_above_272k_tokens_flex": 0.00001125, - "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7 - }, - "gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.5e-7, - "cache_read_input_token_cost_above_272k_tokens": 5e-7, - "cache_read_input_token_cost_flex": 1.3e-7, - "cache_read_input_token_cost_priority": 5e-7, - "input_cost_per_token": 0.0000025, - "input_cost_per_token_above_272k_tokens": 0.000005, - "input_cost_per_token_flex": 0.00000125, - "input_cost_per_token_batches": 0.00000125, - "input_cost_per_token_priority": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "output_cost_per_token_above_272k_tokens": 0.0000225, - "output_cost_per_token_flex": 0.0000075, - "output_cost_per_token_batches": 0.0000075, - "output_cost_per_token_priority": 0.00003, - "regional_processing_uplift_multiplier_eu": 1.1, - "regional_processing_uplift_multiplier_us": 1.1, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none", - "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true, - "input_cost_per_token_above_272k_tokens_flex": 0.0000025, - "output_cost_per_token_above_272k_tokens_flex": 0.00001125, - "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7 - }, - "gpt-5.4-mini": { - "cache_read_input_token_cost": 7.5e-8, - "cache_read_input_token_cost_flex": 3.75e-8, - "cache_read_input_token_cost_priority": 1.5e-7, - "input_cost_per_token": 7.5e-7, - "input_cost_per_token_flex": 3.75e-7, - "input_cost_per_token_batches": 3.75e-7, - "input_cost_per_token_priority": 0.0000015, - "litellm_provider": "openai", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0000045, - "output_cost_per_token_flex": 0.00000225, - "output_cost_per_token_batches": 0.00000225, - "output_cost_per_token_priority": 0.000009, - "regional_processing_uplift_multiplier_eu": 1.1, - "regional_processing_uplift_multiplier_us": 1.1, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -28282,11 +30122,13 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token": 7.5e-7, @@ -28334,11 +30176,13 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-nano": { "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, @@ -28383,11 +30227,13 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token": 2e-7, "input_cost_per_token_flex": 1e-7, @@ -28432,18 +30278,22 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, "gpt-5.5": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "cache_read_input_token_cost_batches": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_priority": 0.0000125, "litellm_provider": "openai", "max_input_tokens": 1050000, @@ -28454,6 +30304,7 @@ "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, + "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, @@ -28490,17 +30341,21 @@ "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, - "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7 + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, + "source": "https://developers.openai.com/api/docs/pricing" }, "gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "cache_read_input_token_cost_batches": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token": 0.000005, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_priority": 0.0000125, "litellm_provider": "openai", "max_input_tokens": 1050000, @@ -28511,6 +30366,7 @@ "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, + "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, @@ -28547,7 +30403,17 @@ "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, - "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7 + "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "gpt-5.5-cyber": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000125, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 0.000075, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true }, "gpt-5.6": { "cache_creation_input_token_cost": 0.000005, @@ -28560,6 +30426,10 @@ "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, + "cache_read_input_token_cost_batches": 2e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-7, + "cache_creation_input_token_cost_batches": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens_batches": 0.000005, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token": 0.000004, @@ -28567,6 +30437,7 @@ "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, + "input_cost_per_token_above_272k_tokens_batches": 0.000004, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "litellm_provider": "openai", @@ -28579,6 +30450,7 @@ "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, + "output_cost_per_token_above_272k_tokens_batches": 0.000015, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, @@ -28651,7 +30523,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", + "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "supports_parallel_function_calling": true }, @@ -28666,6 +30538,10 @@ "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, + "cache_read_input_token_cost_batches": 1e-8, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-8, + "cache_creation_input_token_cost_batches": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-7, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token": 2e-7, @@ -28673,6 +30549,7 @@ "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "input_cost_per_token_batches": 1e-7, + "input_cost_per_token_above_272k_tokens_batches": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_priority": 4e-7, "litellm_provider": "openai", @@ -28685,6 +30562,7 @@ "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "output_cost_per_token_batches": 6e-7, + "output_cost_per_token_above_272k_tokens_batches": 9e-7, "output_cost_per_token_flex": 6e-7, "output_cost_per_token_priority": 0.0000024, "regional_processing_uplift_multiplier_eu": 1.1, @@ -28694,6 +30572,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -28733,6 +30612,10 @@ "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, + "cache_read_input_token_cost_batches": 2e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 4e-7, + "cache_creation_input_token_cost_batches": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens_batches": 0.000005, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token": 0.000004, @@ -28740,6 +30623,7 @@ "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, + "input_cost_per_token_above_272k_tokens_batches": 0.000004, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "litellm_provider": "openai", @@ -28752,6 +30636,7 @@ "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, + "output_cost_per_token_above_272k_tokens_batches": 0.000015, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, @@ -28761,6 +30646,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -28801,6 +30687,10 @@ "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, + "cache_read_input_token_cost_batches": 1e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-7, + "cache_creation_input_token_cost_batches": 0.00000125, + "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000025, "cache_read_input_token_cost_flex": 1e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token": 0.000002, @@ -28808,6 +30698,7 @@ "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_above_272k_tokens_batches": 0.000002, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.000004, "litellm_provider": "openai", @@ -28820,6 +30711,7 @@ "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "output_cost_per_token_batches": 0.000006, + "output_cost_per_token_above_272k_tokens_batches": 0.000009, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.000024, "regional_processing_uplift_multiplier_eu": 1.1, @@ -28829,6 +30721,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -28868,6 +30761,10 @@ "cache_read_input_token_cost_above_272k_tokens": 0.000002, "cache_read_input_token_cost_above_272k_tokens_flex": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000004, + "cache_read_input_token_cost_batches": 5e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 0.000001, + "cache_creation_input_token_cost_batches": 0.00000625, + "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000125, "cache_read_input_token_cost_flex": 5e-7, "cache_read_input_token_cost_priority": 0.000002, "input_cost_per_token": 0.00001, @@ -28875,6 +30772,7 @@ "input_cost_per_token_above_272k_tokens_flex": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00004, "input_cost_per_token_batches": 0.000005, + "input_cost_per_token_above_272k_tokens_batches": 0.00001, "input_cost_per_token_flex": 0.000005, "input_cost_per_token_priority": 0.00002, "litellm_provider": "openai", @@ -28887,6 +30785,7 @@ "output_cost_per_token_above_272k_tokens_flex": 0.0000375, "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 0.000025, + "output_cost_per_token_above_272k_tokens_batches": 0.0000375, "output_cost_per_token_flex": 0.000025, "output_cost_per_token_priority": 0.0001, "regional_processing_uplift_multiplier_eu": 1.1, @@ -28896,6 +30795,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -28926,77 +30826,159 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, - "gpt-audio": { - "deprecation_date": "2027-01-20", - "input_cost_per_audio_token": 0.000032, - "input_cost_per_token": 0.0000025, + "gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-7, + "cache_creation_input_token_cost_flex": 6.25e-8, + "cache_creation_input_token_cost_priority": 2.5e-7, + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-8, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-8, + "cache_read_input_token_cost_batches": 5e-9, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-8, + "cache_creation_input_token_cost_batches": 6.25e-8, + "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-7, + "cache_read_input_token_cost_flex": 5e-9, + "cache_read_input_token_cost_priority": 2e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, + "input_cost_per_token_above_272k_tokens_flex": 1e-7, + "input_cost_per_token_above_272k_tokens_priority": 4e-7, + "input_cost_per_token_batches": 5e-8, + "input_cost_per_token_above_272k_tokens_batches": 1e-7, + "input_cost_per_token_flex": 5e-8, + "input_cost_per_token_priority": 2e-7, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_audio_token": 0.000064, - "output_cost_per_token": 0.00001, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_272k_tokens": 7.5e-7, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-7, + "output_cost_per_token_above_272k_tokens_priority": 0.0000015, + "output_cost_per_token_batches": 2.5e-7, + "output_cost_per_token_above_272k_tokens_batches": 3.75e-7, + "output_cost_per_token_flex": 2.5e-7, + "output_cost_per_token_priority": 0.000001, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" + "/v1/batch", + "/v1/responses" ], "supported_modalities": [ "text", - "audio" + "image" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "gpt-audio-1.5": { - "input_cost_per_audio_token": 0.000032, - "input_cost_per_token": 0.0000025, + "gpt-6-sol": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, + "cache_creation_input_token_cost_flex": 0.00000125, + "cache_creation_input_token_cost_priority": 0.000005, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, + "cache_read_input_token_cost_batches": 1e-7, + "cache_read_input_token_cost_above_272k_tokens_batches": 2e-7, + "cache_creation_input_token_cost_batches": 0.00000125, + "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000025, + "cache_read_input_token_cost_flex": 1e-7, + "cache_read_input_token_cost_priority": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, + "input_cost_per_token_above_272k_tokens_flex": 0.000002, + "input_cost_per_token_above_272k_tokens_priority": 0.000008, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_above_272k_tokens_batches": 0.000002, + "input_cost_per_token_flex": 0.000001, + "input_cost_per_token_priority": 0.000004, "litellm_provider": "openai", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000015, + "output_cost_per_token_above_272k_tokens_flex": 0.0000075, + "output_cost_per_token_above_272k_tokens_priority": 0.00003, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_above_272k_tokens_batches": 0.0000075, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" ], "supported_modalities": [ "text", - "audio" + "image" ], "supported_output_modalities": [ - "text", - "audio" + "text" ], - "supports_audio_input": true, - "supports_audio_output": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, + "supports_none_reasoning_effort": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, - "gpt-audio-2025-08-28": { + "gpt-audio": { "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 0.000032, "input_cost_per_token": 0.0000025, @@ -29007,6 +30989,7 @@ "mode": "chat", "output_cost_per_audio_token": 0.000064, "output_cost_per_token": 0.00001, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -29033,22 +31016,19 @@ "supports_tool_choice": true, "supports_vision": false }, - "gpt-audio-mini": { - "deprecation_date": "2027-01-20", - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, + "gpt-audio-1.5": { + "input_cost_per_audio_token": 0.000032, + "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.00001, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses", - "/v1/realtime", - "/v1/batch" + "/v1/chat/completions" ], "supported_modalities": [ "text", @@ -29070,17 +31050,56 @@ "supports_tool_choice": true, "supports_vision": false }, - "gpt-audio-mini-2025-10-06": { - "deprecation_date": "2026-07-23", - "input_cost_per_audio_token": 0.00001, - "input_cost_per_token": 6e-7, + "gpt-audio-2025-08-28": { + "deprecation_date": "2027-01-20", + "input_cost_per_audio_token": 0.000032, + "input_cost_per_token": 0.0000025, "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 0.00002, - "output_cost_per_token": 0.0000024, + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.00001, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "gpt-audio-mini": { + "deprecation_date": "2027-01-20", + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", @@ -29142,7 +31161,16 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "deprecation_date": "2027-01-20" + "deprecation_date": "2027-01-20", + "source": "https://developers.openai.com/api/docs/pricing" + }, + "gpt-rosalind-research": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://developers.openai.com/api/docs/pricing" }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", @@ -29346,81 +31374,14 @@ "max_input_tokens": 200000, "max_output_tokens": 100000 }, - "groq/gemma-7b-it": { - "input_cost_per_token": 5e-8, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-8, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.1-8b-instant": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5e-8, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8e-8, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "deprecation_date": "2026-08-16", - "input_cost_per_token": 5.9e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 7.9e-7, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "deprecation_date": "2026-03-09", - "input_cost_per_token": 2e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 1.1e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3.4e-7, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/meta-llama/llama-guard-4-12b": { - "deprecation_date": "2026-03-05", + "groq/llama-guard-3-8b": { "input_cost_per_token": 2e-7, "litellm_provider": "groq", "max_input_tokens": 8192, - "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2e-7 + "output_cost_per_token": 2e-7, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" }, "groq/meta-llama/llama-prompt-guard-2-22m": { "input_cost_per_token": 3e-8, @@ -29442,20 +31403,6 @@ "output_cost_per_token": 4e-8, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" }, - "groq/moonshotai/kimi-k2-instruct-0905": { - "deprecation_date": "2026-04-15", - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000003, - "cache_read_input_token_cost": 5e-7, - "litellm_provider": "groq", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "groq/openai/gpt-oss-120b": { "cache_read_input_token_cost": 7.5e-8, "input_cost_per_token": 1.5e-7, @@ -29518,35 +31465,6 @@ "supports_tool_choice": true, "supports_web_search": true }, - "groq/qwen/qwen3-32b": { - "deprecation_date": "2026-07-17", - "input_cost_per_token": 2.9e-7, - "litellm_provider": "groq", - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 5.9e-7, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/qwen/qwen3.6-27b": { - "input_cost_per_token": 6e-7, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-7, "litellm_provider": "groq", @@ -29825,6 +31743,22 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "inception", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "source": "https://docs.inceptionlabs.ai/get-started/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "jamba-1.5": { "input_cost_per_token": 2e-7, "litellm_provider": "ai21", @@ -29987,6 +31921,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -30024,6 +31959,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -30051,6 +31987,46 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512 }, + "jp.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_1hr": 0.0000088, + "cache_read_input_token_cost": 2.2e-7, + "input_cost_per_token": 0.0000044, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000022, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.000004125, "cache_creation_input_token_cost_above_1hr": 0.0000066, @@ -30129,6 +32105,7 @@ "cache_read_input_token_cost": 2.2e-7, "input_cost_per_token": 0.0000022, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -31280,39 +33257,50 @@ "minimax.minimax-m2": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000012, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "minimax.minimax-m2.1": { "input_cost_per_token": 3e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 196000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "minimax/MiniMax-M2": { "input_cost_per_token": 3e-7, @@ -31411,62 +33399,81 @@ "input_cost_per_token": 4e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.000002, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 40000, + "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 0.0000015, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, - "supports_system_messages": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-7, @@ -31502,14 +33509,18 @@ "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0000015, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": true }, "mistral.mistral-small-2402-v1:0": { "input_cost_per_token": 0.000001, @@ -31555,19 +33566,6 @@ "supports_system_messages": true, "supports_native_structured_output": true }, - "mistral/codestral-2405": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 0.000001, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000003, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/codestral-2508": { "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, @@ -31599,6 +33597,7 @@ "supports_tool_choice": true }, "mistral/codestral-mamba-latest": { + "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -31610,22 +33609,8 @@ "supports_assistant_prefill": true, "supports_tool_choice": true }, - "mistral/devstral-2512": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral-2-vibe-cli", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-latest": { + "cache_read_input_token_cost": 4e-8, "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -31639,22 +33624,8 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/devstral-medium-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-medium-latest": { + "cache_read_input_token_cost": 4e-8, "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -31668,37 +33639,8 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/devstral-small-2505": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2507": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/news/devstral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/devstral-small-latest": { + "cache_read_input_token_cost": 1e-8, "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -31721,6 +33663,15 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000044, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -31729,21 +33680,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/labs-devstral-small-2512": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 1e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/labs-leanstral-1-5": { "input_cost_per_token": 0, "litellm_provider": "mistral", @@ -31770,54 +33706,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/magistral-medium-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-medium-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://mistral.ai/news/magistral", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/magistral-medium-latest": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, @@ -31835,38 +33723,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/magistral-small-1-2-2509": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/magistral-small-2506": { - "deprecation_date": "2025-11-30", - "input_cost_per_token": 5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://mistral.ai/pricing#api-pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/magistral-small-latest": { "cache_read_input_token_cost": 1.5e-8, "input_cost_per_token": 1.5e-7, @@ -32029,6 +33885,7 @@ "supports_vision": true }, "mistral/mistral-code-agent-latest": { + "cache_read_input_token_cost": 4e-8, "input_cost_per_token": 4e-7, "litellm_provider": "mistral", "max_input_tokens": 256000, @@ -32072,48 +33929,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/mistral-large-2402": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 0.000004, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000012, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2407": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 0.000003, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000009, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/mistral-large-2512": { "cache_read_input_token_cost": 5e-8, "input_cost_per_token": 5e-7, @@ -32171,6 +33986,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32179,49 +33998,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-2312": { - "deprecation_date": "2025-06-16", - "input_cost_per_token": 0.0000027, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.0000081, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2505": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/mistral-medium-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-2604": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, @@ -32231,6 +34007,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32240,6 +34020,7 @@ "supports_vision": true }, "mistral/mistral-medium-3": { + "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -32247,6 +34028,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32255,22 +34040,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-medium-3-1-2508": { - "deprecation_date": "2026-08-31", - "input_cost_per_token": 4e-7, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://mistral.ai/news/mistral-medium-3", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-medium-3-5": { "cache_read_input_token_cost": 1.5e-7, "input_cost_per_token": 0.0000015, @@ -32280,6 +34049,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32297,6 +34070,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32314,6 +34091,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32323,6 +34104,7 @@ "supports_vision": true }, "mistral/mistral-small": { + "cache_read_input_token_cost": 1e-8, "input_cost_per_token": 1e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -32344,6 +34126,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-7, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32352,22 +34138,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/mistral-small-3-2-2506": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 6e-8, - "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.8e-7, - "source": "https://mistral.ai/pricing", - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/mistral-small-latest": { "cache_read_input_token_cost": 1.5e-8, "input_cost_per_token": 1.5e-7, @@ -32377,6 +34147,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-7, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32386,6 +34160,7 @@ "supports_vision": true }, "mistral/mistral-tiny": { + "cache_read_input_token_cost": 2.5e-8, "input_cost_per_token": 2.5e-7, "litellm_provider": "mistral", "max_input_tokens": 32000, @@ -32406,6 +34181,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-7, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32423,6 +34202,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32440,6 +34223,10 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0000075, + "reasoning_effort_levels": [ + "none", + "high" + ], "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_function_calling": true, @@ -32448,33 +34235,8 @@ "supports_tool_choice": true, "supports_vision": true }, - "mistral/open-codestral-mamba": { - "deprecation_date": "2025-06-06", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 2.5e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/open-mistral-7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 2.5e-7, - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "mistral/open-mistral-nemo": { + "cache_read_input_token_cost": 3e-8, "input_cost_per_token": 3e-7, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -32487,79 +34249,8 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/open-mistral-nemo-2407": { - "deprecation_date": "2026-07-31", - "input_cost_per_token": 3e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x22b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/open-mixtral-8x7b": { - "deprecation_date": "2025-03-30", - "input_cost_per_token": 7e-7, - "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 7e-7, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "mistral/pixtral-12b-2409": { - "deprecation_date": "2025-12-31", - "input_cost_per_token": 1.5e-7, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-7, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "mistral/pixtral-large-2411": { - "deprecation_date": "2026-05-31", - "input_cost_per_token": 0.000002, - "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "mistral/pixtral-large-latest": { + "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.000002, "litellm_provider": "mistral", "max_input_tokens": 128000, @@ -32574,6 +34265,7 @@ "supports_vision": true }, "mistral/voxtral-small-2507": { + "cache_read_input_token_cost": 1e-8, "input_cost_per_second": 0.00006666666666666667, "input_cost_per_token": 1e-7, "litellm_provider": "mistral", @@ -32589,6 +34281,7 @@ "supports_tool_choice": true }, "mistral/voxtral-small-latest": { + "cache_read_input_token_cost": 1e-8, "input_cost_per_second": 0.00006666666666666667, "input_cost_per_token": 1e-7, "litellm_provider": "mistral", @@ -32603,7 +34296,7 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "mistral/zai-glm-5-2": { + "mistral/zai-glm-5": { "cache_read_input_token_cost": 1.4e-7, "input_cost_per_token": 0.0000014, "litellm_provider": "mistral", @@ -32612,7 +34305,12 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.mistral.ai/models/zai-glm-5-2", + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -32620,94 +34318,92 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot.kimi-k2-thinking": { - "input_cost_per_token": 6e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "mistral/zai-glm-5-2": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.0000014, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000025, + "output_cost_per_token": 0.0000044, + "reasoning_effort_levels": [ + "none", + "minimal", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-2", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_system_messages": true, - "supports_native_structured_output": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-0711-preview": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.0000014, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_token": 0.0000044, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-0905-preview": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.0000014, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "output_cost_per_token": 0.0000044, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ], + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "moonshot/kimi-k2-thinking": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-05-25", + "moonshot.kimi-k2-thinking": { "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-thinking-turbo": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 0.00000115, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "moonshot/kimi-k2-turbo-preview": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-05-25", - "input_cost_per_token": 0.00000115, - "litellm_provider": "moonshot", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.000008, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true + "supports_system_messages": true, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "moonshot/kimi-k2.5": { "cache_read_input_token_cost": 1e-7, @@ -32783,9 +34479,7 @@ "supports_video_input": true, "supports_vision": true }, - "moonshot/kimi-latest": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-01-28", + "moonshot/moonshot-v1-128k": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -32795,12 +34489,10 @@ "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "moonshot/kimi-latest-128k": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-01-28", + "moonshot/moonshot-v1-128k-vision-preview": { "input_cost_per_token": 0.000002, "litellm_provider": "moonshot", "max_input_tokens": 131072, @@ -32810,12 +34502,11 @@ "output_cost_per_token": 0.000005, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, - "moonshot/kimi-latest-32k": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-01-28", + "moonshot/moonshot-v1-32k": { "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, @@ -32825,105 +34516,11 @@ "output_cost_per_token": 0.000003, "source": "https://platform.moonshot.ai/docs/pricing", "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "moonshot/kimi-latest-8k": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2026-01-28", - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/kimi-thinking-preview": { - "cache_read_input_token_cost": 1.5e-7, - "deprecation_date": "2025-11-11", - "input_cost_per_token": 6e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", - "supports_vision": true - }, - "moonshot/moonshot-v1-128k": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-128k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-128k-vision-preview": { - "input_cost_per_token": 0.000002, - "litellm_provider": "moonshot", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.000005, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "moonshot/moonshot-v1-32k": { - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-32k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 0.000001, - "litellm_provider": "moonshot", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "moonshot/moonshot-v1-32k-vision-preview": { - "input_cost_per_token": 0.000001, + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 0.000001, "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -32949,19 +34546,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "moonshot/moonshot-v1-8k-0430": { - "deprecation_date": "2024-04-30", - "input_cost_per_token": 2e-7, - "litellm_provider": "moonshot", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://platform.moonshot.ai/docs/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, "moonshot/moonshot-v1-8k-vision-preview": { "input_cost_per_token": 2e-7, "litellm_provider": "moonshot", @@ -32992,16 +34576,38 @@ "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.000003, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true + }, + "moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "morph/morph-v3-fast": { "input_cost_per_token": 8e-7, @@ -33365,6 +34971,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 0.00000132, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 0.00000396, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/google/gemma-3-27b-it": { "max_tokens": 110000, "max_input_tokens": 110000, @@ -33635,6 +35250,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 0.0000014, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -35675,61 +37301,79 @@ "input_cost_per_token": 2e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-7, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-7, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_native_structured_output": true + "supports_audio_input": false, + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "nvidia.nemotron-nano-9b-v2": { "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-7, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-7, "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, "o1": { "cache_read_input_token_cost": 0.0000075, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, + "output_cost_per_token_batches": 0.00003, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, @@ -35744,12 +37388,15 @@ "cache_read_input_token_cost": 0.0000075, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.00006, + "output_cost_per_token_batches": 0.00003, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -35765,6 +37412,7 @@ "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", @@ -35773,6 +37421,7 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { @@ -35780,6 +37429,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", @@ -35809,6 +37459,7 @@ "cache_read_input_token_cost_priority": 8.75e-7, "deprecation_date": "2026-12-11", "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "litellm_provider": "openai", @@ -35817,6 +37468,7 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { @@ -35824,6 +37476,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", @@ -35847,98 +37500,19 @@ "supports_vision": true, "supports_web_search": true }, - "o3-deep-research": { - "cache_read_input_token_cost": 0.0000025, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.00001, - "input_cost_per_token_batches": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.00004, - "output_cost_per_token_batches": 0.00002, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o3-deep-research-2025-06-26": { - "cache_read_input_token_cost": 0.0000025, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.00001, - "input_cost_per_token_batches": 0.000005, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.00004, - "output_cost_per_token_batches": 0.00002, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "o3-mini": { "cache_read_input_token_cost": 5.5e-7, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -35951,12 +37525,15 @@ "cache_read_input_token_cost": 5.5e-7, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -35967,10 +37544,11 @@ }, "o4-mini": { "cache_read_input_token_cost": 2.75e-7, - "cache_read_input_token_cost_flex": 1.375e-7, + "cache_read_input_token_cost_flex": 1.38e-7, "cache_read_input_token_cost_priority": 5e-7, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "litellm_provider": "openai", @@ -35979,6 +37557,7 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { @@ -35986,6 +37565,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, @@ -35998,10 +37578,11 @@ }, "o4-mini-2025-04-16": { "cache_read_input_token_cost": 2.75e-7, - "cache_read_input_token_cost_flex": 1.375e-7, + "cache_read_input_token_cost_flex": 1.38e-7, "cache_read_input_token_cost_priority": 5e-7, "deprecation_date": "2026-10-23", "input_cost_per_token": 0.0000011, + "input_cost_per_token_batches": 5.5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "litellm_provider": "openai", @@ -36010,6 +37591,7 @@ "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 0.0000044, + "output_cost_per_token_batches": 0.0000022, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { @@ -36017,6 +37599,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://developers.openai.com/api/docs/pricing", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_pdf_input": true, @@ -36027,88 +37610,6 @@ "supports_vision": true, "supports_web_search": true }, - "o4-mini-deep-research": { - "cache_read_input_token_cost": 5e-7, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "o4-mini-deep-research-2025-06-26": { - "cache_read_input_token_cost": 5e-7, - "deprecation_date": "2026-07-23", - "input_cost_per_token": 0.000002, - "input_cost_per_token_batches": 0.000001, - "litellm_provider": "openai", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "responses", - "output_cost_per_token": 0.000008, - "output_cost_per_token_batches": 0.000004, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "oci/cohere.command-a-03-2025": { "input_cost_per_token": 0.00000156, "litellm_provider": "oci", @@ -36249,7 +37750,12 @@ "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/google.gemini-2.5-flash-lite": { "input_cost_per_token": 7.5e-8, @@ -36264,7 +37770,12 @@ "supports_response_schema": true, "supports_vision": true, "supports_native_streaming": true, - "supports_image_size": false + "supports_image_size": false, + "supports_reasoning": false, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/google.gemini-2.5-pro": { "input_cost_per_token": 0.00000125, @@ -36278,7 +37789,12 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_vision": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_video_input": true }, "oci/meta.llama-3.1-405b-instruct": { "input_cost_per_token": 0.00001068, @@ -36801,21 +38317,31 @@ "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-7, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-7, - "supports_system_messages": true + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": false }, "openai/container": { "code_interpreter_cost_per_session": 0.03, @@ -36865,65 +38391,67 @@ "supports_vision": false }, "opencode-go/glm-5": { + "litellm_provider": "opencode-go", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "litellm_provider": "opencode-go", "source": "https://opencode.ai", "supported_endpoints": [ "/v1/chat/completions" - ] + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, "opencode-go/glm-5.1": { + "litellm_provider": "opencode-go", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "litellm_provider": "opencode-go", "source": "https://opencode.ai", "supported_endpoints": [ "/v1/chat/completions" - ] + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, "opencode-go/glm-5.2": { + "litellm_provider": "opencode-go", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "litellm_provider": "opencode-go", "source": "https://opencode.ai", "supported_endpoints": [ "/v1/chat/completions" - ] + ], + "supports_function_calling": true, + "supports_reasoning": true }, "opencode-go/glm-5.3": { + "litellm_provider": "opencode-go", "max_input_tokens": 200000, "max_output_tokens": 128000, "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "litellm_provider": "opencode-go", "source": "https://opencode.ai", "supported_endpoints": [ "/v1/chat/completions" - ] + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, "opencode-go/gpt-5.6-luna": { + "litellm_provider": "opencode-go", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "source": "https://opencode.ai", "supported_endpoints": [ "/v1/chat/completions" ], @@ -36947,4683 +38475,10017 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai" + "supports_xhigh_reasoning_effort": true }, "opencode-go/grok-4.5": { + "litellm_provider": "opencode-go", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "opencode-go/hy3": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "opencode-go/hy3-preview": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "opencode-go/kimi-k2.5": { + "litellm_provider": "opencode-go", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "opencode-go/kimi-k2.6": { + "litellm_provider": "opencode-go", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "opencode-go/kimi-k2.7-code": { + "litellm_provider": "opencode-go", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true + }, + "opencode-go/kimi-k3": { + "litellm_provider": "opencode-go", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "opencode-go/mimo-v2-omni": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "opencode-go/mimo-v2-pro": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "opencode-go/mimo-v2.5": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "opencode-go/mimo-v2.5-pro": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "opencode-go/minimax-m2.5": { + "litellm_provider": "opencode-go", + "max_input_tokens": 196608, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_computer_use": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "opencode-go/minimax-m2.7": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1000192, + "max_output_tokens": 1000192, + "max_tokens": 1000192, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": false + }, + "opencode-go/minimax-m3": { + "litellm_provider": "opencode-go", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "opencode-go/qwen3.5-plus": { + "litellm_provider": "opencode-go", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "opencode-go/qwen3.6-plus": { + "litellm_provider": "opencode-go", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "opencode-go/qwen3.7-max": { + "litellm_provider": "opencode-go", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "opencode-go/qwen3.7-plus": { + "litellm_provider": "opencode-go", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "opencode-go/qwen3.8-max": { + "litellm_provider": "opencode-go", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://opencode.ai", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/aion-labs/aion-2.0": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.0": { + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-3.0-mini": { + "cache_read_input_token_cost": 1.8e-7, + "input_cost_per_token": 7e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000014, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/aion-labs/aion-rp-llama-3.1-8b": { + "input_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/amazon/nova-2-lite-v1": { + "input_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-lite-v1": { + "input_cost_per_token": 6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 300000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-micro-v1": { + "input_cost_per_token": 3.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/amazon/nova-premier-v1": { + "cache_read_input_token_cost": 6.25e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/amazon/nova-pro-v1": { + "input_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 300000, + "max_output_tokens": 5120, + "max_tokens": 5120, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/anthracite-org/magnum-v4-72b": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-7, + "cache_creation_input_token_cost_above_1hr": 5e-7, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-fable-5": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 0.000001, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_1hr": 0.00002, + "prompt_cache_min_tokens": 512, + "supports_web_search": true + }, + "openrouter/anthropic/claude-fable-5.1": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "thinking_always_on": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-7, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_1hr": 0.00002, + "prompt_cache_min_tokens": 512, + "supports_web_search": true + }, + "openrouter/anthropic/claude-fable-5.1:batch": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-fable-5:batch": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-haiku-4.5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-haiku-4.5:batch": { + "cache_creation_input_token_cost": 6.25e-7, + "cache_creation_input_token_cost_above_1hr": 0.000001, + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.1:batch": { + "cache_creation_input_token_cost": 0.000009375, + "cache_creation_input_token_cost_above_1hr": 0.000015, + "cache_read_input_token_cost": 7.5e-7, + "input_cost_per_token": 0.0000075, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000375, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.5": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_output_config": true, + "prompt_cache_min_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.5:batch": { + "cache_creation_input_token_cost": 0.000003125, + "cache_creation_input_token_cost_above_1hr": 0.000005, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 4096, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.6:batch": { + "cache_creation_input_token_cost": 0.000003125, + "cache_creation_input_token_cost_above_1hr": 0.000005, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.7": { + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "prompt_cache_min_tokens": 2048, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.7:batch": { + "cache_creation_input_token_cost": 0.000003125, + "cache_creation_input_token_cost_above_1hr": 0.000005, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.8": { + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-7, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-4.8:batch": { + "cache_creation_input_token_cost": 0.000003125, + "cache_creation_input_token_cost_above_1hr": 0.000005, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-5": { + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": false, + "supports_audio_input": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00002, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-opus-5:batch": { + "cache_creation_input_token_cost": 0.000003125, + "cache_creation_input_token_cost_above_1hr": 0.000005, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": false, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.5": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.5:batch": { + "cache_creation_input_token_cost": 0.000001875, + "cache_creation_input_token_cost_above_1hr": 0.000003, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000375, + "cache_read_input_token_cost": 1.5e-7, + "cache_read_input_token_cost_above_200k_tokens": 3e-7, + "input_cost_per_token": 0.0000015, + "input_cost_per_token_above_200k_tokens": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000075, + "output_cost_per_token_above_200k_tokens": 0.00001125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.6": { + "supports_adaptive_thinking": true, + "supports_legacy_thinking": true, + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "prompt_cache_min_tokens": 1024, + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-4.6:batch": { + "cache_creation_input_token_cost": 0.000001875, + "cache_creation_input_token_cost_above_1hr": 0.000003, + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.0000015, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-5": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_sampling_params": false, + "supports_adaptive_thinking": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_1hr": 0.000004, + "supports_web_search": true + }, + "openrouter/anthropic/claude-sonnet-5:batch": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/arcee-ai/trinity-large-thinking": { + "cache_read_input_token_cost": 6e-8, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 80000, + "max_tokens": 80000, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/baidu/ernie-4.5-vl-424b-a47b": { + "deprecation_date": "2026-10-08", + "input_cost_per_token": 4.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 123000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-1.6": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_above_128k_tokens": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000002, + "output_cost_per_token_above_128k_tokens": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-1.6-flash": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2-1-turbo": { + "input_cost_per_token": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-code": { + "deprecation_date": "2026-11-11", + "input_cost_per_token": 5e-7, + "input_cost_per_token_above_128k_tokens": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000003, + "output_cost_per_token_above_128k_tokens": 0.000006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-lite": { + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_above_128k_tokens": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000002, + "output_cost_per_token_above_128k_tokens": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance-seed/seed-2.0-mini": { + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_128k_tokens": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_above_128k_tokens": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": { + "input_cost_per_token": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-a": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r-08-2024": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r-plus-08-2024": { + "input_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/command-r7b-12-2024": { + "input_cost_per_token": 3.75e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/cohere/north-mini-code:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 3.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8.9e-7, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 147456, + "max_tokens": 147456, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_cache_hit": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9.5e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.3e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-r1": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 7e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-r1-0528": { + "cache_read_input_token_cost": 3.5e-7, + "input_cost_per_token": 5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00000215, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-r1-distill-llama-70b": { + "deprecation_date": "2026-09-28", + "input_cost_per_token": 8e-7, + "output_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v3.1-terminus": { + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.000001, + "cache_read_input_token_cost": 1.35e-7, + "deprecation_date": "2026-09-28", + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v3.2": { + "cache_read_input_token_cost": 1.345e-7, + "deprecation_date": "2026-09-28", + "input_cost_per_token": 2.69e-7, + "input_cost_per_token_cache_hit": 1.345e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v3.2-exp": { + "cache_read_input_token_cost": 2e-8, + "deprecation_date": "2026-09-28", + "input_cost_per_token": 2.7e-7, + "input_cost_per_token_cache_hit": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.1e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_assistant_prefill": true, + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-flash": { + "input_cost_per_token": 4.9e-8, + "output_cost_per_token": 9.8e-8, + "cache_read_input_token_cost": 9.8e-9, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-flash-0731": { + "input_cost_per_token": 4e-8, + "output_cost_per_token": 6.4e-7, + "cache_read_input_token_cost": 1.6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-flash-vision-exp": { + "input_cost_per_token": 2.2e-7, + "output_cost_per_token": 6.6e-7, + "cache_read_input_token_cost": 7e-9, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-pro": { + "input_cost_per_token": 8.92272e-7, + "input_cost_per_token_cache_hit": 4.4e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 0.000001784544, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "cache_read_input_token_cost": 7.4356e-8, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4-pro-0813": { + "input_cost_per_token": 0.00000132, + "input_cost_per_token_cache_hit": 1.9272e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 0.00000396, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "cache_read_input_token_cost": 4.4e-8, + "off_peak_pricing": { + "windows": [ + { + "weekdays": [ + "saturday", + "sunday" + ], + "hours_utc": "00:00-00:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "00:00-01:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "04:00-06:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "10:00-00:00" + } + ], + "input_cost_per_token": 6.6e-7, + "output_cost_per_token": 0.00000198, + "cache_read_input_token_cost": 2.2e-8 + }, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/deepseek/deepseek-v4.1-flash": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 6e-9, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "windows": [ + { + "weekdays": [ + "saturday", + "sunday" + ], + "hours_utc": "00:00-00:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "00:00-01:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "04:00-06:00" + }, + { + "weekdays": [ + "monday", + "tuesday", + "wednesday", + "thursday", + "friday" + ], + "hours_utc": "10:00-00:00" + } + ], + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "cache_read_input_token_cost": 3e-9 + }, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/dots-studio/dots-3-note-preview:free": { + "deprecation_date": "2026-12-31", + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 512000, + "max_output_tokens": 460800, + "max_tokens": 460800, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemini-2.5-flash": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 1e-7, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_image_size": false, + "cache_read_input_token_cost": 3e-8, + "deprecation_date": "2026-10-20", + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_pdf_input": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-flash-image": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000025, + "cache_read_input_token_cost": 3e-8, + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 1e-7, + "deprecation_date": "2027-03-15", + "input_cost_per_audio_token": 0.000001, + "output_cost_per_image_token": 0.00003, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": true + }, + "openrouter/google/gemini-2.5-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 3e-8, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1e-8, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 3e-7, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-flash-lite:batch": { + "cache_read_input_audio_token_cost": 3e-8, + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 1.5e-7, + "input_cost_per_token": 5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-flash:batch": { + "cache_read_input_audio_token_cost": 1e-7, + "cache_read_input_token_cost": 3e-8, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-pro": { + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 1.25e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "deprecation_date": "2026-10-20", + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000015, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_pdf_input": true, + "supports_reasoning": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-2.5-pro-preview": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 1.25e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000015, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/google/gemini-2.5-pro-preview-05-06": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost": 3.75e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000015, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true + }, + "openrouter/google/gemini-2.5-pro:batch": { + "cache_read_input_audio_token_cost": 1.25e-7, + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "deprecation_date": "2026-10-20", + "input_cost_per_audio_token": 6.25e-7, + "input_cost_per_token": 6.25e-7, + "input_cost_per_token_above_200k_tokens": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_200k_tokens": 0.0000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3-flash-preview": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 1e-7, + "cache_read_input_token_cost": 5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000003, + "rpm": 2000, + "source": "https://openrouter.ai/api/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000, + "supports_video_input": true + }, + "openrouter/google/gemini-3-flash-preview:batch": { + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3-pro-image": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 2e-7, + "input_cost_per_audio_token": 0.000002, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3-pro-image-preview": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 2e-7, + "input_cost_per_audio_token": 0.000002, + "output_cost_per_image_token": 0.00012, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_tokens": 65535, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "output_cost_per_token_batches": 0.000006, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-image": { + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.000003, + "output_cost_per_image_token": 0.00006, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-image-preview": { + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.000003, + "output_cost_per_image_token": 0.00006, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 5e-8, + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000015, + "output_cost_per_token": 0.0000015, + "rpm": 2000, + "source": "https://openrouter.ai/api/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 + }, + "openrouter/google/gemini-3.1-flash-lite-image": { + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 0.0000015, + "output_cost_per_image_token": 0.00003, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/google/gemini-3.1-flash-lite-preview": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 5e-8, + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000015, + "output_cost_per_token": 0.0000015, + "rpm": 2000, + "source": "https://openrouter.ai/api/v1/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 + }, + "openrouter/google/gemini-3.1-flash-lite:batch": { + "cache_read_input_audio_token_cost": 2.5e-8, + "cache_read_input_token_cost": 1.25e-8, + "input_cost_per_audio_token": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.1-pro-preview": { + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "cache_read_input_audio_token_cost": 2e-7, + "input_cost_per_audio_token": 0.000002, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.1-pro-preview-customtools": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 2e-7, + "input_cost_per_audio_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "output_cost_per_token_above_200k_tokens": 0.000018, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.1-pro-preview:batch": { + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000002, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.000009, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 3e-7, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000009, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_audio_token": 0.000003, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash-lite": { + "cache_creation_input_token_cost": 8.33333333333333e-8, + "cache_read_input_audio_token_cost": 3e-8, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 3e-7, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash-lite:batch": { + "cache_read_input_audio_token_cost": 1.5e-8, + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_audio_token": 1.5e-7, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.5-flash:batch": { + "cache_read_input_audio_token_cost": 1.5e-7, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.0000015, + "input_cost_per_token": 7.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000045, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.6-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, + "output_cost_per_token": 0.00000375, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 7.5e-7, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.6-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 3.75e-8, + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 3.75e-7, + "input_cost_per_token": 3.75e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.7-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, + "output_cost_per_token": 0.00000375, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 7.5e-7, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.7-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 3.75e-8, + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 3.75e-7, + "input_cost_per_token": 3.75e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.8-flash": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, + "output_cost_per_token": 0.00000375, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": true, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 7.5e-7, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemini-3.8-flash:batch": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 3.75e-8, + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 3.75e-7, + "input_cost_per_token": 3.75e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_video_input": true + }, + "openrouter/google/gemma-2-27b-it": { + "input_cost_per_token": 6.5e-7, + "output_cost_per_token": 6.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-3-27b-it": { + "input_cost_per_token": 8e-8, + "output_cost_per_token": 4.5e-7, + "cache_read_input_token_cost": 4e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/google/gemma-3-4b-it": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-26b-a4b-it": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 9e-8, + "output_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-26b-a4b-it:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-31b-it": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 3.4e-7, + "cache_read_input_token_cost": 5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/google/gemma-4-31b-it:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 8e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 3686, + "max_tokens": 3686, + "mode": "chat", + "output_cost_per_token": 1.1e-7, + "supports_tool_choice": false, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/ibm-granite/granite-4.0-h-micro": { + "input_cost_per_token": 1.7e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131000, + "max_output_tokens": 117900, + "max_tokens": 117900, + "mode": "chat", + "output_cost_per_token": 1.12e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/ibm-granite/granite-4.2-8b": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inception/mercury-2": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 50000, + "max_tokens": 50000, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inception/mercury-2.5": { + "cache_read_input_token_cost": 4e-9, + "input_cost_per_token": 4e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 260000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash": { + "cache_read_input_token_cost": 4.2e-9, + "input_cost_per_token": 2.1e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.3e-8, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-fin": { + "cache_read_input_token_cost": 1.2e-8, + "input_cost_per_token": 6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-fin:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-sante:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-vl": { + "cache_read_input_token_cost": 1.2e-8, + "input_cost_per_token": 6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/inclusionai/ling-3.0-flash-vl:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/inference-net/schematron-v2-small": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.3e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/inference-net/schematron-v2-turbo": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 3e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/kwaipilot/kat-coder-pro-v2.5": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 7.4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.00000296, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/liquid/lfm-2.5-2.6b:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_tokens": 6000, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "supports_tool_choice": false, + "max_input_tokens": 8000, + "max_output_tokens": 6000, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meituan/longcat-2.0": { + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048756, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-7, + "litellm_provider": "openrouter", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_tool_choice": true, + "max_input_tokens": 8192, + "max_output_tokens": 8000 + }, + "openrouter/meta-llama/llama-3.1-70b-instruct": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.1-8b-instruct": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 8e-8, + "cache_read_input_token_cost": 2.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2.7e-8, + "output_cost_per_token": 2.01e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 60000, + "max_output_tokens": 54000, + "max_tokens": 54000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.2-3b-instruct": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 3.3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-3.3-70b-instruct": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-4-maverick": { + "input_cost_per_token": 1.875e-7, + "output_cost_per_token": 6.525e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-4-scout": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1310720, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta-llama/llama-guard-4-12b": { + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 1.8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta/muse-glimmer-30b": { + "cache_read_input_token_cost": 4e-8, + "input_cost_per_token": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/meta/muse-spark-1.1": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 0.00000425, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.2": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 0.00000425, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.2-contributor": { + "cache_read_input_token_cost": 2e-9, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.3": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.00000125, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 0.00000425, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/meta/muse-spark-1.3-contributor": { + "cache_read_input_token_cost": 2e-9, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/microsoft/phi-4": { + "input_cost_per_token": 7e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 16384, + "max_output_tokens": 14745, + "max_tokens": 14745, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/microsoft/wizardlm-2-8x22b": { + "input_cost_per_token": 6.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65535, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 6.2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-01": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.0000011, + "litellm_provider": "openrouter", + "max_input_tokens": 1000192, + "max_output_tokens": 900172, + "max_tokens": 900172, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m1": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000022, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2": { + "input_cost_per_token": 2.55e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00000102, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2-her": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 3e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.1": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 3e-8, + "deprecation_date": "2026-10-08", + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_computer_use": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.5": { + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.00000108, + "cache_read_input_token_cost": 2.7e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_computer_use": false, + "supports_pdf_input": false, + "supports_response_schema": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.7": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 6e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m2.7:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 196608, + "max_output_tokens": 176947, + "max_tokens": 176947, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m2.7:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "openrouter/minimax/minimax-m3": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "cache_read_input_token_cost": 6e-8, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/minimax/minimax-m3:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/minimax/minimax-m3:free", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/mistralai/codestral-2508": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 9e-7, + "cache_read_input_token_cost": 3e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/codestral-2508:batch": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 204800, + "max_tokens": 204800, + "mode": "chat", + "output_cost_per_token": 4.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/devstral-2512": { + "cache_read_input_token_cost": 4e-8, + "input_cost_per_image": 0, + "input_cost_per_token": 4e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/ministral-14b-2512": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_image": 0, + "input_cost_per_token": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/ministral-3b-2512": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_image": 0, + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/ministral-8b-2512": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_image": 0, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/ministral-8b-2512:batch": { + "cache_read_input_token_cost": 7.5e-9, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 7.5e-8, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-7, + "litellm_provider": "openrouter", + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.3e-7, + "supports_tool_choice": true, + "max_input_tokens": 32768, + "max_output_tokens": 8191 + }, + "openrouter/mistralai/mistral-large": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "openrouter", + "max_tokens": 102400, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_tool_choice": true, + "max_input_tokens": 128000, + "max_output_tokens": 102400, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-large-2407": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "cache_read_input_token_cost": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-large-2512:batch": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.000002, + "cache_read_input_token_cost": 4e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3-5": { + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.0000075, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3-5:batch": { + "input_cost_per_token": 7.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 0.00000375, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3.1": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.000002, + "cache_read_input_token_cost": 4e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-medium-3.1:batch": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 104857, + "max_tokens": 104857, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-nemo": { + "input_cost_per_token": 1.9e-8, + "output_cost_per_token": 3e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-saba": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 6e-7, + "cache_read_input_token_cost": 2e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-24b-instruct-2501": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 8e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-2603": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "cache_read_input_token_cost": 1.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-2603:batch": { + "cache_read_input_token_cost": 7.5e-9, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 209715, + "max_tokens": 209715, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 3.51e-7, + "litellm_provider": "openrouter", + "max_tokens": 102400, + "mode": "chat", + "output_cost_per_token": 5.55e-7, + "supports_tool_choice": true, + "max_input_tokens": 128000, + "max_output_tokens": 102400, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 9.375e-8, + "litellm_provider": "openrouter", + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, + "litellm_provider": "openrouter", + "max_tokens": 52428, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_tool_choice": true, + "max_input_tokens": 65536, + "max_output_tokens": 52428, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/mistralai/voxtral-small-24b-2507": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "cache_read_input_token_cost": 1e-8, + "input_cost_per_audio_token": 0.0001, + "litellm_provider": "openrouter", + "max_input_tokens": 32768, + "max_output_tokens": 26214, + "max_tokens": 26214, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_pdf_input": true, + "supports_audio_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2": { + "input_cost_per_token": 5.7e-7, + "output_cost_per_token": 0.0000023, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2-0905": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000025, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2-thinking": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000025, + "cache_read_input_token_cost": 1.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 7e-8, + "input_cost_per_token": 4.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "output_cost_per_token": 0.00000225, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2.6": { + "input_cost_per_token": 9.5e-7, + "output_cost_per_token": 0.000004, + "cache_read_input_token_cost": 1.6e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k2.7-code": { + "input_cost_per_token": 7.062e-7, + "output_cost_per_token": 0.0000033, + "cache_read_input_token_cost": 1.8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k3": { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 3e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false + }, + "openrouter/moonshotai/kimi-k3:batch": { + "cache_read_input_token_cost": 2.28e-7, + "input_cost_per_token": 0.00000228, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000114, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/hy3": { - "litellm_provider": "opencode-go", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "openrouter/morph/morph-v3-fast": { + "input_cost_per_token": 8e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 81920, + "max_output_tokens": 38000, + "max_tokens": 38000, "mode": "chat", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false + "output_cost_per_token": 0.0000012, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/hy3-preview": { - "litellm_provider": "opencode-go", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "openrouter/morph/morph-v3-large": { + "input_cost_per_token": 9e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_native_streaming": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "output_cost_per_token": 0.0000019, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/kimi-k2.5": { + "openrouter/nex-agi/nex-n2.5-mini": { + "cache_read_input_token_cost": 2.5e-9, + "input_cost_per_token": 2.5e-8, + "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "supports_function_calling": true, + "output_cost_per_token": 1e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, + "supports_tool_choice": false, "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/kimi-k2.6": { + "openrouter/nex-agi/nex-n2.5-mini:free": { + "deprecation_date": "2026-09-25", + "input_cost_per_token": 0, + "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/kimi-k2.7-code": { + "openrouter/nex-agi/nex-n2.5-pro": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 7.5e-8, + "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "output_cost_per_token": 2.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "opencode-go/kimi-k3": { + "openrouter/nex-agi/nex-n2.5-pro:free": { + "deprecation_date": "2026-09-25", + "input_cost_per_token": 0, + "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/mimo-v2-omni": { - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "openrouter/nousresearch/hermes-3-llama-3.1-405b": { + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_prompt_caching": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/mimo-v2-pro": { - "max_input_tokens": 1048576, + "openrouter/nousresearch/hermes-3-llama-3.1-70b": { + "input_cost_per_token": 7e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, + "output_cost_per_token": 7e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_prompt_caching": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/mimo-v2.5": { - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "openrouter/nousresearch/hermes-4-405b": { + "input_cost_per_token": 0.000001, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.000003, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, "supports_response_schema": true, - "supports_prompt_caching": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/mimo-v2.5-pro": { - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, + "openrouter/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 2e-7, + "cache_read_input_token_cost": 3e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false, "supports_response_schema": true, + "supports_vision": false, "supports_prompt_caching": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/minimax-m2.5": { - "max_input_tokens": 196608, + "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_vision": true, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_response_schema": false, + "supports_web_search": false }, - "opencode-go/minimax-m2.7": { - "max_tokens": 1000192, - "max_input_tokens": 1000192, - "max_output_tokens": 1000192, + "openrouter/nvidia/nemotron-3-super-120b-a12b": { + "input_cost_per_token": 8e-8, + "output_cost_per_token": 4.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": false, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/minimax-m3": { - "max_input_tokens": 512000, - "max_output_tokens": 512000, - "max_tokens": 512000, + "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/qwen3.5-plus": { - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000024, + "cache_read_input_token_cost": 1.2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 182520, + "max_tokens": 182520, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "opencode-go/qwen3.6-plus": { + "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/nvidia/nemotron-3.5-content-safety": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": false, "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_web_search": false }, - "opencode-go/qwen3.7-max": { - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openrouter/nvidia/nemotron-3.5-content-safety:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": false }, - "opencode-go/qwen3.7-plus": { - "max_input_tokens": 991808, - "max_output_tokens": 65536, - "max_tokens": 65536, + "openrouter/nvidia/nemotron-3.5-lightning": { + "cache_read_input_token_cost": 4e-8, + "input_cost_per_token": 7e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_vision": false, + "supports_web_search": false }, - "opencode-go/qwen3.8-max": { - "max_input_tokens": 991808, + "openrouter/nvidia/nemotron-3.5-lightning:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, - "litellm_provider": "opencode-go", - "source": "https://opencode.ai", - "supported_endpoints": [ - "/v1/chat/completions" - ] + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/anthropic/claude-3-haiku": { - "input_cost_per_image": 0.0004, - "input_cost_per_token": 2.5e-7, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, "litellm_provider": "openrouter", "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_function_calling": true, + "output_cost_per_token": 0.0000015, "supports_tool_choice": true, - "supports_vision": true, - "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 0.000003, + "openrouter/openai/gpt-3.5-turbo-0613": { + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000002, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/anthropic/claude-3.7-sonnet": { - "input_cost_per_image": 0.0048, + "openrouter/openai/gpt-3.5-turbo-16k": { "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_reasoning": true, + "output_cost_per_token": 0.000004, "supports_tool_choice": true, - "supports_vision": true + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002, + "litellm_provider": "openrouter", + "max_input_tokens": 4095, + "max_output_tokens": 3685, + "max_tokens": 3685, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": false, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/anthropic/claude-fable-5": { - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00005, + "openrouter/openai/gpt-3.5-turbo:batch": { + "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/anthropic/claude-fable-5", + "output_cost_per_token": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 0.000001, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 0.0000125, - "prompt_cache_min_tokens": 512 + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": true }, - "openrouter/anthropic/claude-fable-5.1": { - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00005, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_tokens": 4096, "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/anthropic/claude-fable-5.1", + "output_cost_per_token": 0.00006, + "supports_tool_choice": true, + "max_input_tokens": 8191, + "max_output_tokens": 4096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": false, - "supports_reasoning": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-7, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 0.0000125, - "prompt_cache_min_tokens": 512 + "supports_vision": false, + "supports_web_search": false }, - "openrouter/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 0.00000125, - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 0.000001, + "openrouter/openai/gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000005, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, + "supports_response_schema": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/anthropic/claude-haiku-4.5" + "supports_web_search": false }, - "openrouter/anthropic/claude-opus-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00001875, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, + "openrouter/openai/gpt-4-turbo-preview": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_response_schema": true, + "supports_vision": false }, - "openrouter/anthropic/claude-opus-4.1": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, + "openrouter/openai/gpt-4-turbo:batch": { + "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000075, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 0.00000625, + "openrouter/openai/gpt-4.1": { "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "input_cost_per_token": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000008, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_output_config": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/anthropic/claude-opus-4.5" + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.0000016, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-4.7": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "openrouter/openai/gpt-4.1-mini:batch": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000025, - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-4.8": { - "input_cost_per_token": 0.000005, - "output_cost_per_token": 0.000025, + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/anthropic/claude-opus-4.8", + "output_cost_per_token": 4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-7, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 0.00000625 + "supports_reasoning": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/anthropic/claude-opus-5": { - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "openrouter/openai/gpt-4.1-nano:batch": { + "cache_read_input_token_cost": 1.25e-8, + "input_cost_per_token": 5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000025, - "source": "https://openrouter.ai/anthropic/claude-opus-5", - "supports_assistant_prefill": false, - "supports_computer_use": true, + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_web_search": true }, - "openrouter/anthropic/claude-sonnet-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, + "openrouter/openai/gpt-4.1:batch": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 0.00000375, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, + "output_cost_per_token": 0.00001, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/anthropic/claude-sonnet-4.5" + "cache_read_input_token_cost": 0.00000125, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_web_search": true }, - "openrouter/anthropic/claude-sonnet-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost": 3e-7, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.000015, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", - "supports_assistant_prefill": true, - "supports_computer_use": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_web_search": true }, - "openrouter/anthropic/claude-sonnet-5": { - "input_cost_per_token": 0.000002, + "openrouter/openai/gpt-4o-2024-08-06": { + "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/anthropic/claude-sonnet-5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, + "supports_web_search": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 0.0000025 - }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "input_cost_per_token": 1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://openrouter.ai/bytedance/ui-tars-1.5-7b", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8.9e-7, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000001, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2e-7, - "input_cost_per_token_cache_hit": 2e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, - "mode": "chat", - "output_cost_per_token": 8e-7, - "supports_assistant_prefill": true, - "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_reasoning": false }, - "openrouter/deepseek/deepseek-r1": { - "input_cost_per_token": 7e-7, - "input_cost_per_token_cache_hit": 1.4e-7, + "openrouter/openai/gpt-4o-2024-11-20": { + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_assistant_prefill": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_reasoning": false }, - "openrouter/deepseek/deepseek-r1-0528": { - "input_cost_per_token": 5e-7, - "input_cost_per_token_cache_hit": 1.4e-7, + "openrouter/openai/gpt-4o-mini": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, "litellm_provider": "openrouter", - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00000215, - "supports_assistant_prefill": true, + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 7.5e-8, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 8e-7, - "output_cost_per_token": 8e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, - "mode": "chat", - "source": "https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_vision": false + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v3.1-terminus": { - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 0.000001, - "cache_read_input_token_cost": 1.35e-7, + "openrouter/openai/gpt-4o-mini-2024-07-18": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "cache_read_input_token_cost": 7.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/deepseek/deepseek-v3.1-terminus", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false }, - "openrouter/deepseek/deepseek-v3.2": { - "input_cost_per_token": 2.69e-7, - "input_cost_per_token_cache_hit": 2.8e-8, + "openrouter/openai/gpt-4o-mini:batch": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_token": 7.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 3e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v3.2-exp": { - "input_cost_per_token": 2.7e-7, - "input_cost_per_token_cache_hit": 2e-8, + "openrouter/openai/gpt-4o:batch": { + "cache_read_input_token_cost": 6.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 4.1e-7, - "supports_assistant_prefill": true, + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v4-flash": { - "input_cost_per_token": 8.778e-8, - "output_cost_per_token": 1.7556e-7, - "cache_read_input_token_cost": 1.7556e-8, + "openrouter/openai/gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/deepseek/deepseek-v4-flash", + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 6.5e-8, - "output_cost_per_token": 1.8e-7, - "cache_read_input_token_cost": 1.6e-8, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.00001, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true }, - "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 2.2e-7, - "output_cost_per_token": 6.6e-7, - "cache_read_input_token_cost": 7e-9, + "openrouter/openai/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.00001, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-image": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.00001, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": false, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 0.00000132, - "input_cost_per_token_cache_hit": 4.4e-8, + "openrouter/openai/gpt-5-image-mini": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000396, - "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", - "supports_function_calling": true, + "output_cost_per_token": 0.000002, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/deepseek/deepseek-v4-pro-0813": { - "input_cost_per_token": 0.00000132, - "input_cost_per_token_cache_hit": 4.4e-8, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000396, - "source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813", + "output_cost_per_token": 0.000002, + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-06-01", - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 1e-7, + "openrouter/openai/gpt-5-mini:batch": { + "cache_read_input_token_cost": 1.25e-8, + "input_cost_per_token": 1.25e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_audio_output": true, + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemini-2.5-flash": { - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 3e-7, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000025, - "supports_audio_output": true, + "output_cost_per_token": 4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_image_size": false, - "cache_read_input_token_cost": 3e-8, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/google/gemini-2.5-flash" + "supports_web_search": true }, - "openrouter/google/gemini-2.5-flash-image": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000025, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 8.33333333333333e-8, - "input_cost_per_audio_token": 0.000001, - "output_cost_per_image_token": 0.00003, + "openrouter/openai/gpt-5-nano:batch": { + "cache_read_input_token_cost": 2.5e-9, + "input_cost_per_token": 2.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-flash-image", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/google/gemini-2.5-flash-lite": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 4e-7, + "openrouter/openai/gpt-5-pro": { + "input_cost_per_token": 0.000015, + "output_cost_per_token": 0.00012, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-flash-lite", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1e-8, - "supports_prompt_caching": true + "supports_prompt_caching": false, + "supports_web_search": true }, - "openrouter/google/gemini-2.5-pro": { - "input_cost_per_audio_token": 7e-7, - "input_cost_per_token": 0.00000125, + "openrouter/openai/gpt-5-pro:batch": { + "input_cost_per_token": 0.0000075, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00001, - "supports_audio_output": true, + "output_cost_per_token": 0.00006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 1.25e-7, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/google/gemini-2.5-pro" + "supports_web_search": true }, - "openrouter/google/gemini-2.5-pro-preview": { + "openrouter/openai/gpt-5.1": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 1.25e-7, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_audio_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000015, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-pro-preview", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true + "supports_audio_input": false, + "cache_read_input_token_cost": 1.25e-7, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-2.5-pro-preview-05-06": { + "openrouter/openai/gpt-5.1-codex": { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 1.25e-7, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_audio_token": 0.00000125, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000015, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "cache_read_input_token_cost": 1.3e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-3-flash-preview": { - "cache_read_input_token_cost": 5e-8, - "input_cost_per_audio_token": 0.000001, - "input_cost_per_token": 5e-7, + "openrouter/openai/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_reasoning_token": 0.000003, - "output_cost_per_token": 0.000003, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", - "image", - "audio", - "video" + "image" ], "supported_output_modalities": [ "text" ], - "supports_audio_output": false, + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "supports_web_search": true }, - "openrouter/google/gemini-3-pro-image": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000012, - "cache_read_input_token_cost": 2e-7, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_audio_token": 0.000002, - "output_cost_per_image_token": 0.00012, + "openrouter/openai/gpt-5.1-codex-mini": { + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 0.000002, + "cache_read_input_token_cost": 3e-8, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3-pro-image", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-3-pro-image-preview": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000012, - "cache_read_input_token_cost": 2e-7, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_audio_token": 0.000002, - "output_cost_per_image_token": 0.00012, + "openrouter/openai/gpt-5.1:batch": { + "cache_read_input_token_cost": 6.25e-8, + "input_cost_per_token": 6.25e-7, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3-pro-image-preview", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/google/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "input_cost_per_token_batches": 0.000001, + "openrouter/openai/gpt-5.2": { + "input_cost_per_image": 0, + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "output_cost_per_token_batches": 0.000006, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, + "output_cost_per_token": 0.000014, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true, "supports_web_search": true }, - "openrouter/google/gemini-3.1-flash-image": { - "input_cost_per_token": 5e-7, - "output_cost_per_token": 0.000003, - "output_cost_per_image_token": 0.00006, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.1-flash-image", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/google/gemini-3.1-flash-image-preview": { - "input_cost_per_token": 5e-7, - "output_cost_per_token": 0.000003, - "output_cost_per_image_token": 0.00006, + "openrouter/openai/gpt-5.2-chat": { + "input_cost_per_image": 0, + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.1-flash-image-preview", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, + "output_cost_per_token": 0.000014, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.1-flash-lite": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, + "openrouter/openai/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.75e-7, + "input_cost_per_token": 0.00000175, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], + "output_cost_per_token": 0.000014, + "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", - "image", - "audio", - "video" + "image" ], "supported_output_modalities": [ "text" ], - "supports_audio_input": true, - "supports_audio_output": false, + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "supports_web_search": true }, - "openrouter/google/gemini-3.1-flash-lite-image": { - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 0.0000015, - "output_cost_per_image_token": 0.00003, + "openrouter/openai/gpt-5.2-pro": { + "input_cost_per_image": 0, + "input_cost_per_token": 0.000021, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.1-flash-lite-image", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 0.000168, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.1-flash-lite-preview": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_audio_token": 5e-7, - "input_cost_per_token": 2.5e-7, + "openrouter/openai/gpt-5.2-pro:batch": { + "input_cost_per_token": 0.0000105, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_reasoning_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, + "output_cost_per_token": 0.000084, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 + "supports_web_search": true }, - "openrouter/google/gemini-3.1-pro-preview": { - "cache_read_input_token_cost": 2e-7, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, - "input_cost_per_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, + "openrouter/openai/gpt-5.2:batch": { + "cache_read_input_token_cost": 8.75e-8, + "input_cost_per_token": 8.75e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000012, - "output_cost_per_token_above_200k_tokens": 0.000018, - "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, + "output_cost_per_token": 0.000007, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.1-pro-preview-customtools": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000012, - "cache_read_input_token_cost": 2e-7, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_audio_token": 0.000002, - "input_cost_per_token_above_200k_tokens": 0.000004, - "output_cost_per_token_above_200k_tokens": 0.000018, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "openrouter/openai/gpt-5.3-codex": { + "input_cost_per_token": 0.00000175, + "output_cost_per_token": 0.000014, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.1-pro-preview-customtools", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true + "supports_audio_input": false, + "cache_read_input_token_cost": 1.75e-7, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.5-flash": { - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000009, + "openrouter/openai/gpt-5.4": { + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.000015, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.5-flash", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1.5e-7, - "supports_prompt_caching": true + "supports_audio_input": false, + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "input_cost_per_token_above_272k_tokens": 0.000005, + "output_cost_per_token_above_272k_tokens": 0.0000225, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.5-flash-lite": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000025, + "openrouter/openai/gpt-5.4-image-2": { + "cache_read_input_token_cost": 0.000002, + "input_cost_per_token": 0.000008, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.5-flash-lite", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": false, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 3e-8, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/google/gemini-3.6-flash": { + "openrouter/openai/gpt-5.4-mini": { "input_cost_per_token": 7.5e-7, - "output_cost_per_token": 0.00000375, + "output_cost_per_token": 0.0000045, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.6-flash", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, + "supports_audio_input": false, "cache_read_input_token_cost": 7.5e-8, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemini-3.7-flash": { - "input_cost_per_token": 7.5e-7, - "output_cost_per_token": 0.00000375, + "openrouter/openai/gpt-5.4-mini:batch": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_token": 3.75e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.7-flash", + "output_cost_per_token": 0.00000225, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-8, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/google/gemini-3.8-flash": { - "input_cost_per_token": 7.5e-7, - "output_cost_per_token": 0.00000375, + "openrouter/openai/gpt-5.4-nano": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.00000125, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemini-3.8-flash", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-8, - "supports_prompt_caching": true - }, - "openrouter/google/gemma-2-27b-it": { - "input_cost_per_token": 6.5e-7, - "output_cost_per_token": 6.5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "source": "https://openrouter.ai/google/gemma-2-27b-it", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-8, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemma-3-12b-it": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 1.5e-7, + "openrouter/openai/gpt-5.4-nano:batch": { + "cache_read_input_token_cost": 1e-8, + "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-3-12b-it", + "output_cost_per_token": 6.25e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemma-3-27b-it": { - "input_cost_per_token": 8e-8, - "output_cost_per_token": 4.5e-7, - "cache_read_input_token_cost": 4e-8, + "openrouter/openai/gpt-5.4-pro": { + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 0.00006, + "output_cost_per_token_above_272k_tokens": 0.00027, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-3-27b-it", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true }, - "openrouter/google/gemma-3-4b-it": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 1e-7, + "openrouter/openai/gpt-5.4-pro:batch": { + "input_cost_per_token": 0.000015, + "input_cost_per_token_above_272k_tokens": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-3-4b-it", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 0.00009, + "output_cost_per_token_above_272k_tokens": 0.000135, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemma-4-26b-a4b-it": { - "input_cost_per_token": 7e-8, - "output_cost_per_token": 3.4e-7, + "openrouter/openai/gpt-5.4:batch": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_272k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_272k_tokens": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it", + "output_cost_per_token": 0.0000075, + "output_cost_per_token_above_272k_tokens": 0.00001125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/google/gemma-4-26b-a4b-it:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/openai/gpt-5.5": { + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it:free", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "input_cost_per_token_above_272k_tokens": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000045, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/google/gemma-4-31b-it": { - "input_cost_per_token": 9e-8, - "output_cost_per_token": 3.4e-7, - "cache_read_input_token_cost": 5e-8, + "openrouter/openai/gpt-5.5-pro": { + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00018, + "input_cost_per_token_above_272k_tokens": 0.00006, + "output_cost_per_token_above_272k_tokens": 0.00027, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-4-31b-it", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true }, - "openrouter/google/gemma-4-31b-it:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/openai/gpt-5.5-pro:batch": { + "input_cost_per_token": 0.000015, + "input_cost_per_token_above_272k_tokens": 0.00003, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/google/gemma-4-31b-it:free", + "output_cost_per_token": 0.00009, + "output_cost_per_token_above_272k_tokens": 0.000135, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 6e-8, - "litellm_provider": "openrouter", - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-8, - "supports_tool_choice": true - }, - "openrouter/mancer/weaver": { - "input_cost_per_token": 4e-7, - "litellm_provider": "openrouter", - "max_tokens": 2000, - "mode": "chat", - "output_cost_per_token": 7.5e-7, - "supports_tool_choice": true, - "max_input_tokens": 8000, - "max_output_tokens": 2000 - }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "input_cost_per_token": 5.9e-7, - "litellm_provider": "openrouter", - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 7.9e-7, "supports_tool_choice": true, - "max_input_tokens": 8192, - "max_output_tokens": 8000 + "supports_vision": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-3.1-70b-instruct": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 4e-7, + "openrouter/openai/gpt-5.5:batch": { + "cache_read_input_token_cost": 2.5e-7, + "cache_read_input_token_cost_above_272k_tokens": 5e-7, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_above_272k_tokens": 0.000005, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-3.1-70b-instruct", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_272k_tokens": 0.0000225, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/meta-llama/llama-3.1-8b-instruct": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 8e-8, - "cache_read_input_token_cost": 2.5e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-3.1-8b-instruct", - "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "openrouter/meta-llama/llama-3.2-1b-instruct": { - "input_cost_per_token": 2.7e-8, - "output_cost_per_token": 2.01e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 60000, - "max_output_tokens": 54000, - "max_tokens": 54000, - "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-3.2-1b-instruct", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_vision": false - }, - "openrouter/meta-llama/llama-3.2-3b-instruct": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 3.3e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-3.2-3b-instruct", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-3.3-70b-instruct": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3.2e-7, + "openrouter/openai/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-7, + "cache_creation_input_token_cost_above_272k_tokens": 5e-7, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.0000012, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-3.3-70b-instruct", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-8, + "cache_read_input_token_cost_above_272k_tokens": 4e-8, + "input_cost_per_token_above_272k_tokens": 4e-7, + "output_cost_per_token_above_272k_tokens": 0.0000018, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-4-maverick": { + "openrouter/openai/gpt-5.6-luna-pro": { "input_cost_per_token": 2e-7, - "output_cost_per_token": 6.96e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 2e-8, + "cache_creation_input_token_cost": 2.5e-7, + "cache_creation_input_token_cost_above_272k_tokens": 5e-7, + "input_cost_per_token_above_272k_tokens": 4e-7, + "output_cost_per_token_above_272k_tokens": 0.0000018, + "cache_read_input_token_cost_above_272k_tokens": 4e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 115200, - "max_tokens": 115200, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-4-maverick", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-4-scout": { + "openrouter/openai/gpt-5.6-luna-pro:batch": { + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-4-scout", + "output_cost_per_token": 6e-7, + "output_cost_per_token_above_272k_tokens": 9e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/meta-llama/llama-guard-4-12b": { - "input_cost_per_token": 1.8e-7, - "output_cost_per_token": 1.8e-7, + "openrouter/openai/gpt-5.6-luna:batch": { + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/meta-llama/llama-guard-4-12b", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 6e-7, + "output_cost_per_token_above_272k_tokens": 9e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-01": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.0000011, + "openrouter/openai/gpt-5.6-sol": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "default_reasoning_effort": "medium", + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 1000192, - "max_output_tokens": 900172, - "max_tokens": 900172, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-01", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_vision": true + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000015, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ], + "source": "https://openrouter.ai/api/v1/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 5.5e-7, - "output_cost_per_token": 0.0000022, + "openrouter/openai/gpt-5.6-sol-pro": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.000004, + "output_cost_per_token_above_272k_tokens": 0.000015, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 40000, - "max_tokens": 40000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m1", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 2.55e-7, + "openrouter/openai/gpt-5.6-sol-pro:batch": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_above_272k_tokens": 2e-7, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_272k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 204800, - "max_tokens": 204800, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000102, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_272k_tokens": 0.0000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m2-her": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_read_input_token_cost": 3e-8, + "openrouter/openai/gpt-5.6-sol:batch": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_above_272k_tokens": 2e-7, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_272k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2-her", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_prompt_caching": true + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_272k_tokens": 0.0000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 3e-8, + "openrouter/openai/gpt-5.6-terra": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, "litellm_provider": "openrouter", - "max_input_tokens": 204000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": false, - "supports_computer_use": false + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "input_cost_per_token_above_272k_tokens": 0.000004, + "output_cost_per_token_above_272k_tokens": 0.000018, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 2.7e-7, - "output_cost_per_token": 0.00000108, - "cache_read_input_token_cost": 2.7e-8, + "openrouter/openai/gpt-5.6-terra-pro": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000012, + "cache_read_input_token_cost": 2e-7, + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.000004, + "output_cost_per_token_above_272k_tokens": 0.000018, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_computer_use": false + "supports_web_search": true }, - "openrouter/minimax/minimax-m2.7": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "cache_read_input_token_cost": 6e-8, + "openrouter/openai/gpt-5.6-terra-pro:batch": { + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_above_272k_tokens": 2e-7, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_272k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.7", + "output_cost_per_token": 0.000006, + "output_cost_per_token_above_272k_tokens": 0.000009, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m2.7:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/openai/gpt-5.6-terra:batch": { + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_above_272k_tokens": 2e-7, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_272k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 176947, - "max_tokens": 176947, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.7:free", + "output_cost_per_token": 0.000006, + "output_cost_per_token_above_272k_tokens": 0.000009, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/minimax/minimax-m3": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, + "openrouter/openai/gpt-5:batch": { + "cache_read_input_token_cost": 6.25e-8, + "input_cost_per_token": 6.25e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 512000, - "max_tokens": 512000, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m3", + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "cache_read_input_token_cost": 6e-8, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/minimax/minimax-m3:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/openai/gpt-6-astra": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00005, + "cache_read_input_token_cost": 0.000001, + "cache_creation_input_token_cost": 0.0000125, + "input_cost_per_token_above_272k_tokens": 0.00002, + "output_cost_per_token_above_272k_tokens": 0.000075, + "cache_read_input_token_cost_above_272k_tokens": 0.000002, + "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m3:free", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/mistralai/codestral-2508": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 9e-7, - "cache_read_input_token_cost": 3e-8, + "openrouter/openai/gpt-6-astra-pro": { + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00005, + "cache_read_input_token_cost": 0.000001, + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_272k_tokens": 0.000025, + "input_cost_per_token_above_272k_tokens": 0.00002, + "output_cost_per_token_above_272k_tokens": 0.000075, + "cache_read_input_token_cost_above_272k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/mistralai/codestral-2508", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, + "supports_vision": true, "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/mistralai/devstral-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 4e-7, + "openrouter/openai/gpt-6-astra-pro:batch": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.00001, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000002, + "output_cost_per_token": 0.000025, + "output_cost_per_token_above_272k_tokens": 0.0000375, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": true, + "supports_web_search": true }, - "openrouter/mistralai/ministral-14b-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 2e-7, + "openrouter/openai/gpt-6-astra:batch": { + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.00001, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-7, + "output_cost_per_token": 0.000025, + "output_cost_per_token_above_272k_tokens": 0.0000375, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "openrouter/mistralai/ministral-3b-2512": { - "input_cost_per_image": 0, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token": 1e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_272k_tokens": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "openrouter/mistralai/ministral-8b-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-7, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.5e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_272k_tokens": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/mistralai/mistral-7b-instruct": { - "input_cost_per_token": 1.3e-7, - "litellm_provider": "openrouter", - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.3e-7, - "supports_tool_choice": true, - "max_input_tokens": 32768, - "max_output_tokens": 8191 - }, - "openrouter/mistralai/mistral-large": { - "input_cost_per_token": 0.000002, - "litellm_provider": "openrouter", - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 0.000006, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 8191 + "supports_vision": true, + "supports_web_search": true }, - "openrouter/mistralai/mistral-large-2407": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-large-2407", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, "supports_pdf_input": true, - "supports_prompt_caching": true - }, - "openrouter/mistralai/mistral-large-2512": { - "input_cost_per_image": 0, - "input_cost_per_token": 5e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/mistralai/mistral-medium-3": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.000002, - "cache_read_input_token_cost": 4e-8, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-medium-3", - "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/mistralai/mistral-medium-3-5": { - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.0000075, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-medium-3-5", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true + "supports_web_search": true }, - "openrouter/mistralai/mistral-medium-3.1": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.000002, - "cache_read_input_token_cost": 4e-8, + "openrouter/openai/gpt-audio": { + "input_cost_per_token": 0.0000025, + "output_cost_per_token": 0.00001, + "input_cost_per_audio_token": 0.000032, + "output_cost_per_audio_token": 0.000064, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-medium-3.1", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_vision": false, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/mistralai/mistral-nemo": { - "input_cost_per_token": 1.9e-8, - "output_cost_per_token": 3e-8, + "openrouter/openai/gpt-audio-mini": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000024, + "input_cost_per_audio_token": 6e-7, + "output_cost_per_audio_token": 0.0000024, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-nemo", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": false, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/mistralai/mistral-saba": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 6e-7, - "cache_read_input_token_cost": 2e-8, + "openrouter/openai/gpt-chat-latest": { + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.00003, + "cache_read_input_token_cost": 5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-saba", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": false, + "supports_vision": true, "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/mistralai/mistral-small-24b-instruct-2501": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 8e-8, + "openrouter/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/mistralai/mistral-small-2603": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "cache_read_input_token_cost": 1.5e-8, + "openrouter/openai/gpt-oss-20b": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 1.8e-8, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/mistralai/mistral-small-2603", + "output_cost_per_token": 9e-8, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 3.51e-7, + "openrouter/openai/gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-8, + "output_cost_per_token": 3e-7, + "cache_read_input_token_cost": 3.75e-8, "litellm_provider": "openrouter", - "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 5.55e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "max_input_tokens": 131072, - "max_output_tokens": 131072 + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 7.5e-8, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, "litellm_provider": "openrouter", - "max_tokens": 128000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 2e-7, + "output_cost_per_token": 0.00006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 128000 + "supports_vision": true, + "supports_web_search": true }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "input_cost_per_token": 0.000002, + "openrouter/openai/o1-pro": { + "input_cost_per_token": 0.00015, + "output_cost_per_token": 0.0006, "litellm_provider": "openrouter", - "max_tokens": 65536, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.000006, - "supports_tool_choice": true, - "max_input_tokens": 65536, - "max_output_tokens": 65536 + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_tool_choice": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true }, - "openrouter/mistralai/voxtral-small-24b-2507": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "cache_read_input_token_cost": 1e-8, - "input_cost_per_audio_token": 0.0001, + "openrouter/openai/o3": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000008, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/mistralai/voxtral-small-24b-2507", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, + "supports_vision": true, "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-7, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2": { - "input_cost_per_token": 5.7e-7, - "output_cost_per_token": 0.0000023, + "openrouter/openai/o3-mini": { + "input_cost_per_token": 0.0000011, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 100352, - "max_tokens": 100352, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k2", + "output_cost_per_token": 0.0000044, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-7, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2-0905": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 0.0000011, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 100352, - "max_tokens": 100352, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k2-0905", + "output_cost_per_token": 0.0000044, "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, + "supports_vision": false, + "cache_read_input_token_cost": 5.5e-7, + "supports_prompt_caching": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_pdf_input": true, "supports_response_schema": true, - "supports_vision": false + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2-thinking": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, - "cache_read_input_token_cost": 1.5e-7, + "openrouter/openai/o3-mini:batch": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 5.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 100352, - "max_tokens": 100352, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k2-thinking", + "output_cost_per_token": 0.0000022, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 7e-8, - "input_cost_per_token": 4.5e-7, + "openrouter/openai/o3-pro": { + "input_cost_per_token": 0.00002, + "output_cost_per_token": 0.00008, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "output_cost_per_token": 0.00000225, - "source": "https://openrouter.ai/moonshotai/kimi-k2.5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 9.5e-7, - "output_cost_per_token": 0.000004, - "cache_read_input_token_cost": 1.6e-7, + "openrouter/openai/o3:batch": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k2.6", + "output_cost_per_token": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_parallel_function_calling": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 6.6e-7, - "output_cost_per_token": 0.0000034, - "cache_read_input_token_cost": 1.8e-7, + "openrouter/openai/o4-mini": { + "input_cost_per_token": 0.0000011, + "output_cost_per_token": 0.0000044, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k2.7-code", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_parallel_function_calling": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2.75e-7, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, - "cache_read_input_token_cost": 3e-7, + "openrouter/openai/o4-mini-high": { + "input_cost_per_token": 0.0000011, + "output_cost_per_token": 0.0000044, + "cache_read_input_token_cost": 2.75e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/moonshotai/kimi-k3", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/nvidia/nemotron-3-nano-30b-a3b": { - "input_cost_per_token": 5e-8, - "output_cost_per_token": 2e-7, - "cache_read_input_token_cost": 3e-8, + "openrouter/openai/o4-mini:batch": { + "cache_read_input_token_cost": 1.375e-7, + "input_cost_per_token": 5.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b", + "output_cost_per_token": 0.0000022, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { + "openrouter/openrouter/auto": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 2000000, + "max_tokens": 2000000, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true, - "supports_audio_input": true + "supports_audio_input": true, + "supports_video_input": true }, - "openrouter/nvidia/nemotron-3-super-120b-a12b": { - "input_cost_per_token": 8.5e-8, - "output_cost_per_token": 4e-7, + "openrouter/openrouter/bodybuilder": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat" }, - "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { + "openrouter/openrouter/free": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 200000, + "max_tokens": 200000, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": true }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { - "input_cost_per_token": 6.25e-7, - "output_cost_per_token": 0.000003125, - "cache_read_input_token_cost": 1.875e-7, + "openrouter/perceptron/perceptron-mk1": { + "input_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.0000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/perplexity/sonar": { + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 127072, + "max_output_tokens": 114364, + "max_tokens": 114364, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-deep-research": { + "input_cost_per_token": 0.000002, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 115200, + "max_tokens": 115200, + "mode": "chat", + "output_cost_per_token": 0.000008, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_vision": false + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": true }, - "openrouter/nvidia/nemotron-3.5-content-safety": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 2e-7, + "openrouter/perplexity/sonar-pro": { + "input_cost_per_token": 0.000003, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety", + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/perplexity/sonar-pro-search": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/nvidia/nemotron-3.5-content-safety:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 0.000002, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 115200, + "max_tokens": 115200, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free", + "output_cost_per_token": 0.000008, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": false, - "supports_tool_choice": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_vision": true + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/nvidia/nemotron-3.5-lightning": { - "input_cost_per_token": 8e-8, + "openrouter/poolside/laguna-s-2.1": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 1.8e-7, + "cache_read_input_token_cost": 9e-9, "litellm_provider": "openrouter", - "max_input_tokens": 262144, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false }, - "openrouter/nvidia/nemotron-3.5-lightning:free": { + "openrouter/poolside/laguna-s-2.1:free": { "input_cost_per_token": 0, "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning:free", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 5e-7, + "openrouter/poolside/laguna-xs-2.1": { + "input_cost_per_token": 6e-8, + "output_cost_per_token": 1.2e-7, + "cache_read_input_token_cost": 3e-8, "litellm_provider": "openrouter", - "max_tokens": 4096, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.0000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/openai/gpt-3.5-turbo" + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "input_cost_per_token": 0.000003, + "openrouter/poolside/laguna-xs-2.1:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_tokens": 4096, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096 + "supports_reasoning": true, + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-3.5-turbo-instruct": { - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "openrouter/prism-ml/ternary-bonsai-2-27b": { + "input_cost_per_token": 7.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-3.5-turbo-instruct", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/openai/gpt-4": { - "input_cost_per_token": 0.00003, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00006, "supports_tool_choice": true, - "max_input_tokens": 8191, - "max_output_tokens": 4096 + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/gpt-4-turbo": { - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "openrouter/qwen/qwen-2.5-72b-instruct": { + "input_cost_per_token": 3.6e-7, + "output_cost_per_token": 4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4-turbo", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4-turbo-preview": { - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "openrouter/qwen/qwen-2.5-7b-instruct": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4.1": { - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000002, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 6.6e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, "mode": "chat", - "output_cost_per_token": 0.000008, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 4e-7, + "openrouter/qwen/qwen-plus": { + "input_cost_per_token": 2.6e-7, + "output_cost_per_token": 7.8e-7, + "cache_read_input_token_cost": 5.2e-8, + "cache_creation_input_token_cost": 3.25e-7, + "input_cost_per_token_above_256k_tokens": 7.8e-7, + "output_cost_per_token_above_256k_tokens": 0.00000234, + "cache_read_input_token_cost_above_256k_tokens": 1.56e-7, + "cache_creation_input_token_cost_above_256k_tokens": 9.75e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1047576, + "max_input_tokens": 1000000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.0000016, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 1e-7, + "openrouter/qwen/qwen-plus-2025-07-28": { + "cache_creation_input_token_cost": 3.25e-7, + "cache_read_input_token_cost": 5.2e-8, + "input_cost_per_token": 2.6e-7, + "output_cost_per_token": 7.8e-7, + "input_cost_per_token_above_256k_tokens": 7.8e-7, + "output_cost_per_token_above_256k_tokens": 0.00000234, "litellm_provider": "openrouter", - "max_input_tokens": 1047576, + "max_input_tokens": 1000000, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 4e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/openai/gpt-4o": { - "input_cost_per_token": 0.0000025, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 0.00000125, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/openai/gpt-4o" + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4o-2024-05-13": { - "input_cost_per_token": 0.000005, + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 6.3e-7, "supports_tool_choice": true, "supports_vision": true }, - "openrouter/openai/gpt-4o-2024-08-06": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 0.00000125, + "openrouter/qwen/qwen2.5-vl-72b-instruct": { + "input_cost_per_token": 8e-7, + "output_cost_per_token": 0.000001, + "cache_read_input_token_cost": 4e-7, "litellm_provider": "openrouter", "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 115200, + "max_tokens": 115200, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4o-2024-08-06", - "supports_function_calling": true, - "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_tool_choice": false, "supports_response_schema": true, - "supports_web_search": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4o-2024-11-20": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 0.00000125, + "openrouter/qwen/qwen3-14b": { + "input_cost_per_token": 1.2e-7, + "output_cost_per_token": 2.4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4o-2024-11-20", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4o-mini": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, + "openrouter/qwen/qwen3-235b-a22b": { + "input_cost_per_token": 4.55e-7, + "output_cost_per_token": 0.00000182, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4o-mini", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-8, - "supports_prompt_caching": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-4o-mini-2024-07-18": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, - "cache_read_input_token_cost": 7.5e-8, + "openrouter/qwen/qwen3-235b-a22b-2507": { + "cache_read_input_token_cost": 1.75e-8, + "input_cost_per_token": 8.75e-8, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4o-mini-2024-07-18", + "output_cost_per_token": 3.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { + "input_cost_per_token": 2.3e-7, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "output_cost_per_token": 0.00001, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 0.0000023, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "openrouter/qwen/qwen3-30b-a3b": { + "input_cost_per_token": 1.2e-7, + "output_cost_per_token": 5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.00001, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { + "input_cost_per_token": 4.815e-8, + "output_cost_per_token": 1.9305e-7, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 32000, + "max_tokens": 32000, "mode": "chat", - "output_cost_per_token": 0.00001, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-8, - "input_cost_per_token": 2.5e-7, + "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.0000024, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 81920, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 0.000002, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5-nano": { - "cache_read_input_token_cost": 5e-9, - "input_cost_per_token": 5e-8, + "openrouter/qwen/qwen3-32b": { + "input_cost_per_token": 8e-8, + "output_cost_per_token": 2.8e-7, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 4e-7, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5-pro": { - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.00012, + "openrouter/qwen/qwen3-8b": { + "input_cost_per_token": 1.17e-7, + "output_cost_per_token": 4.55e-7, "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5-pro", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.1": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.00001, + "openrouter/qwen/qwen3-coder": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 3e-7, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.1", - "supports_function_calling": true, + "output_cost_per_token": 0.000001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_tool_choice": true, - "supports_reasoning": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.25e-7, - "supports_prompt_caching": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.1-codex": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.00001, - "cache_read_input_token_cost": 1.3e-7, + "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 7e-8, + "output_cost_per_token": 2.8e-7, "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.1-codex", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-7, - "input_cost_per_token": 0.00000125, + "openrouter/qwen/qwen3-coder-flash": { + "input_cost_per_token": 1.95e-7, + "output_cost_per_token": 9.75e-7, + "cache_read_input_token_cost": 3.9e-8, + "cache_creation_input_token_cost": 2.4375e-7, + "input_cost_per_token_above_128k_tokens": 5.2e-7, + "output_cost_per_token_above_128k_tokens": 0.0000026, + "cache_read_input_token_cost_above_128k_tokens": 1.04e-7, + "cache_creation_input_token_cost_above_128k_tokens": 6.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00001, - "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.1-codex-mini": { - "input_cost_per_token": 2.5e-7, - "output_cost_per_token": 0.000002, - "cache_read_input_token_cost": 3e-8, + "openrouter/qwen/qwen3-coder-next": { + "input_cost_per_token": 1.2e-7, + "output_cost_per_token": 8e-7, + "cache_read_input_token_cost": 7e-8, "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.1-codex-mini", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.2": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, + "openrouter/qwen/qwen3-coder-plus": { + "cache_creation_input_token_cost": 8.125e-7, + "cache_read_input_token_cost": 1.3e-7, + "input_cost_per_token": 6.5e-7, + "input_cost_per_token_above_128k_tokens": 0.00000195, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000014, + "output_cost_per_token": 0.00000325, + "output_cost_per_token_above_128k_tokens": 0.00000975, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, - "supports_reasoning": true, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.2-chat": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, + "openrouter/qwen/qwen3-max": { + "input_cost_per_token": 7.8e-7, + "output_cost_per_token": 0.0000039, + "cache_read_input_token_cost": 1.56e-7, + "cache_creation_input_token_cost": 9.75e-7, + "input_cost_per_token_above_128k_tokens": 0.00000195, + "output_cost_per_token_above_128k_tokens": 0.00000975, + "cache_read_input_token_cost_above_128k_tokens": 3.9e-7, + "cache_creation_input_token_cost_above_128k_tokens": 0.0000024375, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000014, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/openai/gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-7, - "input_cost_per_token": 0.00000175, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000014, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.2-pro": { - "input_cost_per_image": 0, - "input_cost_per_token": 0.000021, + "openrouter/qwen/qwen3-max-thinking": { + "input_cost_per_token": 7.8e-7, + "output_cost_per_token": 0.0000039, + "input_cost_per_token_above_128k_tokens": 0.00000195, + "output_cost_per_token_above_128k_tokens": 0.00000975, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.000168, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": false, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.3-codex": { - "input_cost_per_token": 0.00000175, - "output_cost_per_token": 0.000014, + "openrouter/qwen/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 9e-8, + "output_cost_per_token": 0.0000011, + "cache_read_input_token_cost": 7e-8, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.3-codex", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.75e-7, - "supports_prompt_caching": true + "supports_vision": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.4": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.000015, + "openrouter/qwen/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 0.0000012, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.4", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-7, - "supports_prompt_caching": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.4-mini": { - "input_cost_per_token": 7.5e-7, - "output_cost_per_token": 0.0000045, + "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 2.1e-7, + "output_cost_per_token": 0.0000019, + "cache_read_input_token_cost": 1e-7, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.4-mini", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-8, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_web_search": false }, - "openrouter/openai/gpt-5.4-nano": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.00000125, + "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.4-nano", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-8, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/openai/gpt-5.4-pro": { - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 0.00006, - "output_cost_per_token_above_272k_tokens": 0.00027, + "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 5.2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.4-pro", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true + "supports_web_search": false }, - "openrouter/openai/gpt-5.5": { - "input_cost_per_token": 0.000005, - "output_cost_per_token": 0.00003, + "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 0.0000024, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-7, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/openai/gpt-5.5-pro": { - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 0.00006, - "output_cost_per_token_above_272k_tokens": 0.00027, + "openrouter/qwen/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.04e-7, + "output_cost_per_token": 4.16e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.5-pro", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true + "supports_web_search": false }, - "openrouter/openai/gpt-5.6-luna": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.0000012, + "openrouter/qwen/qwen3-vl-8b-instruct": { + "input_cost_per_token": 1.17e-7, + "output_cost_per_token": 4.55e-7, "litellm_provider": "openrouter", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.6-luna", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_tool_choice": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-8, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/openai/gpt-5.6-terra": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000012, + "openrouter/qwen/qwen3-vl-8b-thinking": { + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 0.0000021, "litellm_provider": "openrouter", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-5.6-terra", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/openai/gpt-6-astra": { - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00005, - "cache_read_input_token_cost": 0.000001, - "cache_creation_input_token_cost": 0.0000125, - "input_cost_per_token_above_272k_tokens": 0.00002, - "output_cost_per_token_above_272k_tokens": 0.000075, - "cache_read_input_token_cost_above_272k_tokens": 0.000002, - "cache_creation_input_token_cost_above_272k_tokens": 0.000025, + "openrouter/qwen/qwen3.5-122b-a10b": { + "input_cost_per_token": 2.6e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-6-astra", + "output_cost_per_token": 0.00000208, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/openai/gpt-audio": { - "input_cost_per_token": 0.0000025, - "output_cost_per_token": 0.00001, - "input_cost_per_audio_token": 0.000032, - "output_cost_per_audio_token": 0.000064, + "openrouter/qwen/qwen3.5-27b": { + "input_cost_per_token": 1.95e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-audio", + "output_cost_per_token": 0.00000156, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/gpt-audio-mini": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000024, - "input_cost_per_audio_token": 6e-7, - "output_cost_per_audio_token": 0.0000024, + "openrouter/qwen/qwen3.5-35b-a3b": { + "input_cost_per_token": 3.125e-7, "litellm_provider": "openrouter", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-audio-mini", + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, + "supports_reasoning": true, "supports_tool_choice": true, + "supports_vision": true, + "cache_read_input_token_cost": 1.5625e-7, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true + "supports_web_search": false }, - "openrouter/openai/gpt-oss-120b": { - "input_cost_per_token": 3.7e-8, + "openrouter/qwen/qwen3.5-397b-a17b": { + "cache_read_input_token_cost": 2.25e-7, + "input_cost_per_token": 5.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 1.7e-7, - "source": "https://openrouter.ai/openai/gpt-oss-120b", + "output_cost_per_token": 0.0000035, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/gpt-oss-20b": { - "input_cost_per_token": 3e-8, + "openrouter/qwen/qwen3.5-9b": { + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.3e-7, - "source": "https://openrouter.ai/openai/gpt-oss-20b", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/gpt-oss-safeguard-20b": { - "input_cost_per_token": 7.5e-8, - "output_cost_per_token": 3e-7, - "cache_read_input_token_cost": 3.75e-8, + "openrouter/qwen/qwen3.5-flash-02-23": { + "input_cost_per_token": 6.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-oss-safeguard-20b", + "output_cost_per_token": 2.6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/o1": { - "cache_read_input_token_cost": 0.0000075, - "input_cost_per_token": 0.000015, + "openrouter/qwen/qwen3.5-plus-02-15": { + "input_cost_per_token": 2.6e-7, + "input_cost_per_token_above_256k_tokens": 5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.00006, + "output_cost_per_token": 0.00000156, + "output_cost_per_token_above_256k_tokens": 0.000003, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "openrouter/openai/o1-pro": { - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, + "openrouter/qwen/qwen3.5-plus-20260420": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000018, + "cache_creation_input_token_cost": 3.75e-7, + "input_cost_per_token_above_256k_tokens": 3.75e-7, + "output_cost_per_token_above_256k_tokens": 0.00000225, + "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/o1-pro", - "supports_function_calling": false, - "supports_tool_choice": false, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true + "supports_web_search": false }, - "openrouter/openai/o3": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000008, + "openrouter/qwen/qwen3.6-27b": { + "input_cost_per_token": 3.2e-7, + "output_cost_per_token": 0.0000027, + "cache_read_input_token_cost": 1.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 262144, + "max_output_tokens": 262140, + "max_tokens": 262140, "mode": "chat", - "source": "https://openrouter.ai/openai/o3", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-7, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/openai/o3-mini": { - "input_cost_per_token": 0.0000011, + "openrouter/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 0.000001, + "cache_read_input_token_cost": 5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 262144, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 0.0000044, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-7, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, "supports_prompt_caching": true, - "source": "https://openrouter.ai/openai/o3-mini" + "supports_web_search": false }, - "openrouter/openai/o3-mini-high": { - "input_cost_per_token": 0.0000011, + "openrouter/qwen/qwen3.6-flash": { + "input_cost_per_token": 1.875e-7, + "output_cost_per_token": 0.000001125, + "cache_creation_input_token_cost": 2.34375e-7, + "input_cost_per_token_above_256k_tokens": 7.5e-7, + "output_cost_per_token_above_256k_tokens": 0.000003, + "cache_creation_input_token_cost_above_256k_tokens": 9.375e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 0.0000044, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_tool_choice": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/qwen/qwen3.6-max-preview": { + "input_cost_per_token": 0.000001027, + "output_cost_per_token": 0.000006162, + "cache_creation_input_token_cost": 0.00000128375, + "input_cost_per_token_above_128k_tokens": 0.00000158, + "output_cost_per_token_above_128k_tokens": 0.00000948, + "cache_creation_input_token_cost_above_128k_tokens": 0.000001975, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": false, - "cache_read_input_token_cost": 5.5e-7, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/openai/o3-mini-high" + "supports_web_search": false }, - "openrouter/openai/o3-pro": { - "input_cost_per_token": 0.00002, - "output_cost_per_token": 0.00008, + "openrouter/qwen/qwen3.6-plus": { + "cache_creation_input_token_cost": 4.0625e-7, + "input_cost_per_token": 3.25e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/o3-pro", + "output_cost_per_token": 0.00000195, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true + "supports_web_search": false }, - "openrouter/openai/o4-mini": { - "input_cost_per_token": 0.0000011, - "output_cost_per_token": 0.0000044, + "openrouter/qwen/qwen3.7-flash": { + "input_cost_per_token": 3e-8, + "output_cost_per_token": 1.3e-7, + "cache_read_input_token_cost": 6e-9, + "cache_creation_input_token_cost": 3.8e-8, + "input_cost_per_token_above_256k_tokens": 2e-7, + "output_cost_per_token_above_256k_tokens": 8e-7, + "cache_read_input_token_cost_above_256k_tokens": 4e-8, + "cache_creation_input_token_cost_above_256k_tokens": 2.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/openai/o4-mini", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.75e-7, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/openai/o4-mini-high": { - "input_cost_per_token": 0.0000011, - "output_cost_per_token": 0.0000044, - "cache_read_input_token_cost": 2.75e-7, + "openrouter/qwen/qwen3.7-max": { + "input_cost_per_token": 0.000001475, + "output_cost_per_token": 0.000004425, + "cache_read_input_token_cost": 2.95e-7, + "cache_creation_input_token_cost": 0.00000184375, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/openai/o4-mini-high", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/openrouter/auto": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/qwen/qwen3.7-plus": { + "input_cost_per_token": 3.2e-7, + "output_cost_per_token": 0.00000128, "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true - }, - "openrouter/openrouter/bodybuilder": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "chat" + "cache_read_input_token_cost": 6.4e-8, + "supports_prompt_caching": true, + "cache_creation_input_token_cost": 4e-7, + "supports_audio_input": false, + "supports_pdf_input": false, + "supports_web_search": false }, - "openrouter/openrouter/free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/qwen/qwen3.8-2.4t-a95b": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "cache_read_input_token_cost": 2.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_tokens": 200000, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/poolside/laguna-s-2.1": { - "input_cost_per_token": 9e-8, - "output_cost_per_token": 1.8e-7, - "cache_read_input_token_cost": 9e-9, + "openrouter/qwen/qwen3.8-27b": { + "input_cost_per_token": 4.2e-7, + "output_cost_per_token": 0.000003, + "cache_read_input_token_cost": 8.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/poolside/laguna-s-2.1", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/poolside/laguna-s-2.1:free": { + "openrouter/qwen/qwen3.8-27b:free": { "input_cost_per_token": 0, - "output_cost_per_token": 0, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 235929, + "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/poolside/laguna-s-2.1:free", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_vision": false + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/poolside/laguna-xs-2.1": { - "input_cost_per_token": 6e-8, - "output_cost_per_token": 1.2e-7, - "cache_read_input_token_cost": 3e-8, + "openrouter/qwen/qwen3.8-flash": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 4.7e-7, + "cache_read_input_token_cost": 1.6e-8, + "cache_creation_input_token_cost": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/poolside/laguna-xs-2.1", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/poolside/laguna-xs-2.1:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/qwen/qwen3.8-max": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "cache_read_input_token_cost": 2.5e-7, + "cache_creation_input_token_cost": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/poolside/laguna-xs-2.1:free", + "source": "https://openrouter.ai/qwen/qwen3.8-max", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": false + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true }, - "openrouter/qwen/qwen-2.5-72b-instruct": { - "input_cost_per_token": 3.6e-7, - "output_cost_per_token": 4e-7, + "openrouter/qwen/qwen3.8-max-0902": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "cache_read_input_token_cost": 2.5e-7, + "cache_creation_input_token_cost": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen-2.5-72b-instruct", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_vision": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/qwen/qwen-2.5-7b-instruct": { + "openrouter/rekaai/reka-edge": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, + "max_input_tokens": 16384, + "max_output_tokens": 14745, + "max_tokens": 14745, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen-2.5-7b-instruct", + "output_cost_per_token": 1e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/rekaai/reka-flash-3": { + "input_cost_per_token": 1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 58982, + "max_tokens": 58982, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 6.6e-7, + "openrouter/relace/relace-apply-3": { + "input_cost_per_token": 8.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 33792, - "max_output_tokens": 33792, - "max_tokens": 33792, + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000001, - "supports_tool_choice": true + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen-plus": { - "input_cost_per_token": 2.6e-7, - "output_cost_per_token": 7.8e-7, - "cache_read_input_token_cost": 5.2e-8, - "cache_creation_input_token_cost": 3.25e-7, - "input_cost_per_token_above_256k_tokens": 7.8e-7, - "output_cost_per_token_above_256k_tokens": 0.00000234, - "cache_read_input_token_cost_above_256k_tokens": 1.56e-7, - "cache_creation_input_token_cost_above_256k_tokens": 9.75e-7, + "openrouter/relace/relace-search": { + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 256000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen-plus", + "output_cost_per_token": 0.000003, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen-plus-2025-07-28": { - "input_cost_per_token": 2.6e-7, - "output_cost_per_token": 7.8e-7, - "input_cost_per_token_above_256k_tokens": 7.8e-7, - "output_cost_per_token_above_256k_tokens": 0.00000234, + "openrouter/sakana/fugu-max": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.000002, "litellm_provider": "openrouter", "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen-plus-2025-07-28", + "output_cost_per_token": 0.000006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/qwen/qwen-vl-plus": { - "input_cost_per_token": 2.1e-7, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.3e-7, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen2.5-vl-72b-instruct": { - "input_cost_per_token": 8e-7, - "output_cost_per_token": 0.000001, - "cache_read_input_token_cost": 4e-7, + "openrouter/sakana/fugu-ultra": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.00001, "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct", - "supports_function_calling": false, - "supports_tool_choice": false, + "output_cost_per_token": 0.00003, + "output_cost_per_token_above_272k_tokens": 0.000045, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 1.2e-7, - "output_cost_per_token": 2.4e-7, + "openrouter/sakana/fugu-ultra-v2": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_272k_tokens": 0.000001, + "input_cost_per_token": 0.000005, + "input_cost_per_token_above_272k_tokens": 0.00001, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-14b", + "output_cost_per_token": 0.00003, + "output_cost_per_token_above_272k_tokens": 0.000045, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-235b-a22b": { - "input_cost_per_token": 4.55e-7, - "output_cost_per_token": 0.00000182, + "openrouter/sakana/sakana-namazu": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 9.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b", + "output_cost_per_token": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 8.75e-8, + "openrouter/sao10k/l3-lunaris-8b": { + "input_cost_per_token": 4e-8, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 8192, + "max_output_tokens": 7372, + "max_tokens": 7372, "mode": "chat", - "output_cost_per_token": 3.5e-7, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", - "supports_function_calling": true, - "supports_tool_choice": true + "output_cost_per_token": 5e-8, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 2.3e-7, + "openrouter/sao10k/l3.1-euryale-70b": { + "input_cost_per_token": 8.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 0.0000023, - "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", + "output_cost_per_token": 8.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-30b-a3b": { - "input_cost_per_token": 1.2e-7, - "output_cost_per_token": 5e-7, + "openrouter/sao10k/l3.3-euryale-70b": { + "input_cost_per_token": 6.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-30b-a3b", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, + "output_cost_per_token": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 4.815e-8, - "output_cost_per_token": 1.9305e-7, + "openrouter/stepfun/step-3.5-flash": { + "input_cost_per_token": 1e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507", + "output_cost_per_token": 3e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { + "openrouter/stepfun/step-3.7-flash": { + "cache_read_input_token_cost": 4e-8, "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.0000024, "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 262144, + "max_output_tokens": 230400, + "max_tokens": 230400, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507", + "output_cost_per_token": 0.00000115, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3-32b": { - "input_cost_per_token": 8e-8, - "output_cost_per_token": 2.8e-7, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-32b", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false + "output_cost_per_token": 0.0000034, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true }, - "openrouter/qwen/qwen3-8b": { - "input_cost_per_token": 1.17e-7, - "output_cost_per_token": 4.55e-7, + "openrouter/tencent/hunyuan-a13b-instruct": { + "input_cost_per_token": 1.4e-7, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-8b", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 5.7e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-coder": { - "input_cost_per_token": 3e-7, + "openrouter/tencent/hy-mt2-1.8b": { + "input_cost_per_token": 4.4e-8, "litellm_provider": "openrouter", - "max_input_tokens": 262100, - "max_output_tokens": 262100, - "max_tokens": 262100, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 0.000001, - "source": "https://openrouter.ai/qwen/qwen3-coder", - "supports_tool_choice": true, - "supports_function_calling": true + "output_cost_per_token": 1.77e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { - "input_cost_per_token": 7e-8, - "output_cost_per_token": 2.8e-7, + "openrouter/tencent/hy-mt2-30b-a3b": { + "input_cost_per_token": 7.4e-8, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 2.95e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-coder-flash": { - "input_cost_per_token": 1.95e-7, - "output_cost_per_token": 9.75e-7, - "cache_read_input_token_cost": 3.9e-8, - "cache_creation_input_token_cost": 2.4375e-7, - "input_cost_per_token_above_128k_tokens": 5.2e-7, - "output_cost_per_token_above_128k_tokens": 0.0000026, - "cache_read_input_token_cost_above_128k_tokens": 1.04e-7, - "cache_creation_input_token_cost_above_128k_tokens": 6.5e-7, + "openrouter/tencent/hy-mt2-7b": { + "input_cost_per_token": 7.4e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.95e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/tencent/hy3": { + "cache_read_input_token_cost": 3.3e-8, + "input_cost_per_token": 1.32e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 262144, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-coder-flash", + "off_peak_pricing": { + "hours_utc": "16:00-00:00", + "input_cost_per_token": 8.25e-8, + "output_cost_per_token": 3.3e-7, + "cache_read_input_token_cost": 2.0625e-8 + }, + "output_cost_per_token": 5.28e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3-coder-next": { - "input_cost_per_token": 1.2e-7, - "output_cost_per_token": 8e-7, - "cache_read_input_token_cost": 7e-8, + "openrouter/tencent/hy3-preview": { + "cache_read_input_token_cost": 6e-8, + "input_cost_per_token": 1.8e-7, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-coder-next", + "output_cost_per_token": 6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_response_schema": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3-coder-plus": { - "input_cost_per_token": 6.5e-7, + "openrouter/tencent/hy4-preview": { + "cache_read_input_token_cost": 4.2e-8, + "input_cost_per_token": 8.34e-7, "litellm_provider": "openrouter", - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1048576, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 0.00000325, - "source": "https://openrouter.ai/qwen/qwen3-coder-plus", + "output_cost_per_token": 0.000002501, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-max": { - "input_cost_per_token": 7.8e-7, - "output_cost_per_token": 0.0000039, - "cache_read_input_token_cost": 1.56e-7, - "cache_creation_input_token_cost": 9.75e-7, - "input_cost_per_token_above_128k_tokens": 0.00000195, - "output_cost_per_token_above_128k_tokens": 0.00000975, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-7, - "cache_creation_input_token_cost_above_128k_tokens": 0.0000024375, + "openrouter/thedrummer/cydonia-24b-v4.1": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 3e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-max", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, + "supports_tool_choice": false, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3-max-thinking": { - "input_cost_per_token": 7.8e-7, - "output_cost_per_token": 0.0000039, - "input_cost_per_token_above_128k_tokens": 0.00000195, - "output_cost_per_token_above_128k_tokens": 0.00000975, + "openrouter/thedrummer/skyfall-36b-v2": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 5.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-max-thinking", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-next-80b-a3b-instruct": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 0.0000011, - "cache_read_input_token_cost": 7e-8, + "openrouter/thedrummer/unslopnemo-12b": { + "input_cost_per_token": 4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 1024000, + "max_output_tokens": 819200, + "max_tokens": 819200, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 4e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, + "supports_tool_choice": false, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3-next-80b-a3b-thinking": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 0.0000012, + "openrouter/thinkingmachines/inkling": { + "cache_read_input_token_cost": 1.7e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1048576, + "max_output_tokens": 471859, + "max_tokens": 471859, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking", + "output_cost_per_token": 0.00000405, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { - "input_cost_per_token": 2.1e-7, - "output_cost_per_token": 0.0000019, + "openrouter/thinkingmachines/inkling-small": { "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct", + "output_cost_per_token": 0.0000012, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.000004, + "openrouter/thinkingmachines/inkling-small:free": { + "input_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 6e-7, + "openrouter/thinkingmachines/inkling:free": { + "input_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { - "input_cost_per_token": 2e-7, - "output_cost_per_token": 0.0000024, + "openrouter/unbiased/pareto": { + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.0000025, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking", + "output_cost_per_token": 0.0000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_response_schema": false, "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-32b-instruct": { - "input_cost_per_token": 1.04e-7, - "output_cost_per_token": 4.16e-7, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 3.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_tokens": 5529, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-32b-instruct", - "supports_function_calling": true, - "supports_tool_choice": true, + "output_cost_per_token": 6.5e-7, + "supports_tool_choice": false, + "max_input_tokens": 6144, + "max_output_tokens": 5529, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, "supports_response_schema": true, - "supports_vision": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-8b-instruct": { - "input_cost_per_token": 1.17e-7, - "output_cost_per_token": 4.55e-7, + "openrouter/upstage/solar-pro-3": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 1.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 131072, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-8b-instruct", + "output_cost_per_token": 6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3-vl-8b-thinking": { - "input_cost_per_token": 1.8e-7, - "output_cost_per_token": 0.0000021, + "openrouter/upstage/solar-pro4": { + "cache_read_input_token_cost": 1.8e-8, + "input_cost_per_token": 9e-8, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 524288, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3-vl-8b-thinking", + "output_cost_per_token": 3.6e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 2.9e-7, + "openrouter/writer/palmyra-x5": { + "input_cost_per_token": 6e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1040000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 0.0000024, - "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", + "output_cost_per_token": 0.000006, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 0.000003, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/x-ai/grok-4", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 1.95e-7, + "openrouter/x-ai/grok-4.20": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, "mode": "chat", - "output_cost_per_token": 0.00000156, - "source": "https://openrouter.ai/qwen/qwen3.5-27b", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000005, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 2.5e-7, + "openrouter/x-ai/grok-4.20-multi-agent": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 2000000, + "max_output_tokens": 1800000, + "max_tokens": 1800000, "mode": "chat", - "output_cost_per_token": 0.00000125, - "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", - "supports_function_calling": true, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": false, + "supports_tool_choice": false, "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000005, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-397b-a17b": { - "input_cost_per_token": 5.5e-7, + "openrouter/x-ai/grok-4.3": { + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.0000025, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, "mode": "chat", - "output_cost_per_token": 0.0000035, - "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000005, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-9b": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1.5e-7, + "openrouter/x-ai/grok-4.3:batch": { + "cache_read_input_token_cost": 1.6e-7, + "cache_read_input_token_cost_above_200k_tokens": 3.2e-7, + "input_cost_per_token": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_input_tokens": 1000000, + "max_output_tokens": 900000, + "max_tokens": 900000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.5-9b", + "output_cost_per_token": 0.000002, + "output_cost_per_token_above_200k_tokens": 0.000004, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 6.5e-8, + "openrouter/x-ai/grok-4.5": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 2.6e-7, - "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token_above_200k_tokens": 0.000004, + "output_cost_per_token_above_200k_tokens": 0.000012, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 2.6e-7, - "input_cost_per_token_above_256k_tokens": 5e-7, + "openrouter/x-ai/grok-4.6": { + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 0.00000156, - "output_cost_per_token_above_256k_tokens": 0.000003, - "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000004, + "output_cost_per_token_above_200k_tokens": 0.000012, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.5-plus-20260420": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000018, - "cache_creation_input_token_cost": 3.75e-7, - "input_cost_per_token_above_256k_tokens": 3.75e-7, - "output_cost_per_token_above_256k_tokens": 0.00000225, - "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-7, + "openrouter/x-ai/grok-4.7": { + "cache_read_input_token_cost": 4e-7, + "cache_read_input_token_cost_above_200k_tokens": 8e-7, + "input_cost_per_token": 0.0000016, + "input_cost_per_token_above_200k_tokens": 0.0000032, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.5-plus-20260420", + "output_cost_per_token": 0.0000048, + "output_cost_per_token_above_200k_tokens": 0.0000096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3e-7, + "openrouter/x-ai/grok-build-0.1": { + "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, - "cache_read_input_token_cost": 3e-8, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 256000, + "max_output_tokens": 230400, + "max_tokens": 230400, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.6-27b", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_pdf_input": true, + "supports_audio_input": false, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token_above_200k_tokens": 0.000002, + "output_cost_per_token_above_200k_tokens": 0.000004, + "supports_prompt_caching": true, + "supports_web_search": true }, - "openrouter/qwen/qwen3.6-35b-a3b": { + "openrouter/xiaomi/mimo-v2-flash": { "input_cost_per_token": 1e-7, - "output_cost_per_token": 9e-7, - "cache_read_input_token_cost": 5e-8, + "output_cost_per_token": 3e-7, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1e-8, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.6-35b-a3b", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_vision": false, "supports_prompt_caching": true }, - "openrouter/qwen/qwen3.6-flash": { - "input_cost_per_token": 1.875e-7, - "output_cost_per_token": 0.000001125, - "cache_creation_input_token_cost": 2.34375e-7, - "input_cost_per_token_above_256k_tokens": 7.5e-7, - "output_cost_per_token_above_256k_tokens": 0.000003, - "cache_creation_input_token_cost_above_256k_tokens": 9.375e-7, + "openrouter/xiaomi/mimo-v2.5": { + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 2.8e-7, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.8e-9, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.6-flash", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_pdf_input": false, + "supports_video_input": true, "supports_response_schema": true, - "supports_vision": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3.6-max-preview": { - "input_cost_per_token": 0.000001027, - "output_cost_per_token": 0.000006162, - "cache_creation_input_token_cost": 0.00000128375, - "input_cost_per_token_above_128k_tokens": 0.00000158, - "output_cost_per_token_above_128k_tokens": 0.00000948, - "cache_creation_input_token_cost_above_128k_tokens": 0.000001975, + "openrouter/xiaomi/mimo-v2.5-pro": { + "input_cost_per_token": 4.35e-7, + "output_cost_per_token": 8.7e-7, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 3.6e-9, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1050000, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.6-max-preview", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_vision": false, "supports_response_schema": true, - "supports_vision": false + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3.6-plus": { - "input_cost_per_token": 3.25e-7, + "openrouter/xiaomi/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-9, + "input_cost_per_token": 1.4e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.00000195, - "source": "https://openrouter.ai/qwen/qwen3.6-plus", + "output_cost_per_token": 2.8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3.7-flash": { - "input_cost_per_token": 3e-8, - "output_cost_per_token": 1.3e-7, - "cache_read_input_token_cost": 6e-9, - "cache_creation_input_token_cost": 3.8e-8, - "input_cost_per_token_above_256k_tokens": 2e-7, - "output_cost_per_token_above_256k_tokens": 8e-7, - "cache_read_input_token_cost_above_256k_tokens": 4e-8, - "cache_creation_input_token_cost_above_256k_tokens": 2.5e-7, + "openrouter/xiaomi/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-9, + "input_cost_per_token": 4.35e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.7-flash", + "output_cost_per_token": 8.7e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3.7-max": { - "input_cost_per_token": 0.000001475, - "output_cost_per_token": 0.000004425, - "cache_read_input_token_cost": 2.95e-7, - "cache_creation_input_token_cost": 0.00000184375, + "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": { + "cache_read_input_token_cost": 3.6e-8, + "input_cost_per_token": 0.00000435, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.7-max", + "output_cost_per_token": 0.0000087, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.5": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000022, + "cache_read_input_token_cost": 1.1e-7, + "deprecation_date": "2026-12-31", + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3.7-plus": { - "input_cost_per_token": 3.2e-7, - "output_cost_per_token": 0.00000128, + "openrouter/z-ai/glm-4.5-air": { + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 8.5e-7, + "cache_read_input_token_cost": 2.5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_web_search": false + }, + "openrouter/z-ai/glm-4.5v": { + "input_cost_per_token": 6e-7, + "output_cost_per_token": 0.0000018, + "cache_read_input_token_cost": 1.1e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.7-plus", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "cache_read_input_token_cost": 6.4e-8, "supports_prompt_caching": true, - "cache_creation_input_token_cost": 4e-7 + "supports_web_search": false }, - "openrouter/qwen/qwen3.8-2.4t-a95b": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, - "cache_read_input_token_cost": 2.5e-7, + "openrouter/z-ai/glm-4.6": { + "input_cost_per_token": 4.3e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 204800, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b", + "output_cost_per_token": 0.00000175, + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_tool_choice": true, + "cache_read_input_token_cost": 8e-8, + "supports_audio_input": false, + "supports_pdf_input": false, "supports_response_schema": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-7, - "output_cost_per_token": 0.000003, - "cache_read_input_token_cost": 8.5e-8, + "openrouter/z-ai/glm-4.6:exacto": { + "input_cost_per_token": 4.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 202800, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 0.0000019, + "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/z-ai/glm-4.6v": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 9e-7, + "cache_read_input_token_cost": 5.5e-8, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-27b", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/qwen/qwen3.8-flash": { - "input_cost_per_token": 1.5e-7, - "output_cost_per_token": 4.7e-7, - "cache_read_input_token_cost": 1.6e-8, - "cache_creation_input_token_cost": 2e-7, + "openrouter/z-ai/glm-4.7": { + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.00000175, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 8e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, + "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-flash", + "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_assistant_prefill": true, + "supports_audio_input": false, + "supports_pdf_input": false, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/qwen/qwen3.8-max": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, - "cache_read_input_token_cost": 2.5e-7, - "cache_creation_input_token_cost": 0.0000025, + "openrouter/z-ai/glm-4.7-flash": { + "input_cost_per_token": 6.05e-8, + "output_cost_per_token": 4e-7, + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1e-8, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 200000, + "max_output_tokens": 117964, + "max_tokens": 117964, "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-max", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_vision": false, + "supports_prompt_caching": false, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/switchpoint/router": { - "input_cost_per_token": 8.5e-7, + "openrouter/z-ai/glm-5": { + "cache_read_input_token_cost": 1.2e-7, + "input_cost_per_token": 6e-7, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 204800, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.0000034, - "source": "https://openrouter.ai/switchpoint/router", - "supports_tool_choice": true + "output_cost_per_token": 0.00000192, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 4.5e-7, + "openrouter/z-ai/glm-5-turbo": { + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.000004, + "cache_read_input_token_cost": 2.4e-7, + "deprecation_date": "2098-12-31", "litellm_provider": "openrouter", - "max_tokens": 4096, + "max_input_tokens": 202752, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, - "max_input_tokens": 6144, - "max_output_tokens": 4096 + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/x-ai/grok-4": { - "input_cost_per_token": 0.000003, + "openrouter/z-ai/glm-5.1": { + "input_cost_per_token": 9.66e-7, + "output_cost_per_token": 0.000003036, + "cache_read_input_token_cost": 1.794e-7, + "cache_creation_input_token_cost": 0, "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 204800, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, - "source": "https://openrouter.ai/x-ai/grok-4", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_vision": false, + "supports_web_search": false }, - "openrouter/x-ai/grok-4.20": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.0000025, + "openrouter/z-ai/glm-5.2": { + "input_cost_per_token": 6.496e-7, + "output_cost_per_token": 0.0000020416, + "cache_read_input_token_cost": 1.2064e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-4.20", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/x-ai/grok-4.20-multi-agent": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.0000025, + "openrouter/z-ai/glm-5.2:free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_input_tokens": 32768, + "max_output_tokens": 29491, + "max_tokens": 29491, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": false, + "supports_pdf_input": false, + "supports_prompt_caching": false, "supports_tool_choice": false, "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true + "supports_response_schema": false, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/x-ai/grok-4.3": { - "input_cost_per_token": 0.00000125, - "output_cost_per_token": 0.0000025, + "openrouter/z-ai/glm-5.3": { + "input_cost_per_token": 6.538e-7, + "output_cost_per_token": 0.0000020548, + "cache_read_input_token_cost": 1.2142e-7, "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "max_tokens": 1000000, + "max_input_tokens": 1310720, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-4.3", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true + "supports_parallel_function_calling": true, + "supports_pdf_input": false, + "supports_vision": false, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/x-ai/grok-4.5": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "openrouter/z-ai/glm-5.3-flash": { + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 5e-7, + "cache_read_input_token_cost": 5e-8, "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-4.5", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_response_schema": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 3e-7, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/x-ai/grok-4.6": { - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "openrouter/z-ai/glm-5.3-flash:batch": { + "cache_read_input_token_cost": 1.2e-8, + "input_cost_per_token": 6e-8, "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 500000, - "max_tokens": 500000, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-4.6", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-7, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/x-ai/grok-build-0.1": { - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000002, + "openrouter/z-ai/glm-5.3-flashx": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 3.7e-7, "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/x-ai/grok-build-0.1", + "output_cost_per_token": 0.00000125, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-7, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 1e-7, - "output_cost_per_token": 3e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1e-8, + "openrouter/z-ai/glm-5.3:batch": { + "cache_read_input_token_cost": 1.2e-7, + "input_cost_per_token": 7.2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 0.0000024, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": false, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 1.4e-7, - "output_cost_per_token": 2.8e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 2.8e-9, + "openrouter/z-ai/glm-5v-turbo": { + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.000004, + "cache_read_input_token_cost": 2.4e-7, + "deprecation_date": "2098-12-31", "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_vision": true, + "supports_prompt_caching": true, + "supports_web_search": false }, - "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 4.35e-7, - "output_cost_per_token": 8.7e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 3.6e-9, + "openrouter/~anthropic/claude-fable-latest": { + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_1hr": 0.00002, + "cache_read_input_token_cost": 2.5e-7, + "input_cost_per_token": 0.00001, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 0.00005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_vision": false, "supports_response_schema": true, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-4.5": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000022, - "cache_read_input_token_cost": 1.1e-7, + "openrouter/~anthropic/claude-haiku-latest": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-4.5", + "output_cost_per_token": 0.000005, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-4.5-air": { - "input_cost_per_token": 1.3e-7, - "output_cost_per_token": 8.5e-7, - "cache_read_input_token_cost": 2.5e-8, + "openrouter/~anthropic/claude-opus-latest": { + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-4.5-air", + "output_cost_per_token": 0.00002, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-4.5v": { - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000018, - "cache_read_input_token_cost": 1.1e-7, + "openrouter/~anthropic/claude-sonnet-latest": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_1hr": 0.000004, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000002, "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-4.5v", + "output_cost_per_token": 0.00001, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 5.5e-7, + "openrouter/~deepseek/deepseek-flash-latest": { + "cache_read_input_token_cost": 3.6e-9, + "input_cost_per_token": 1.2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 0.0000022, - "source": "https://openrouter.ai/z-ai/glm-4.6", + "output_cost_per_token": 4.8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false }, - "openrouter/z-ai/glm-4.6:exacto": { - "input_cost_per_token": 4.5e-7, + "openrouter/~deepseek/deepseek-pro-latest": { + "cache_read_input_token_cost": 1.2726e-8, + "input_cost_per_token": 3.9996e-7, "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 0.0000019, - "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", + "output_cost_per_token": 0.00000119988, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, - "openrouter/z-ai/glm-4.6v": { - "input_cost_per_token": 3e-7, - "output_cost_per_token": 9e-7, - "cache_read_input_token_cost": 5.5e-8, + "openrouter/~deepseek/deepseek-v4-flash-latest": { + "cache_read_input_token_cost": 8e-9, + "input_cost_per_token": 3e-8, "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_input_tokens": 1310720, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-4.6v", + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false + }, + "openrouter/~google/gemini-flash-latest": { + "cache_creation_input_token_cost": 4.16666666666667e-8, + "cache_read_input_audio_token_cost": 7.5e-8, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 7.5e-7, + "input_cost_per_token": 7.5e-7, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00000375, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": true }, - "openrouter/z-ai/glm-4.7": { - "input_cost_per_token": 4e-7, - "output_cost_per_token": 0.00000175, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 8e-8, + "openrouter/~google/gemini-pro-latest": { + "cache_creation_input_token_cost": 3.75e-7, + "cache_read_input_audio_token_cost": 2e-7, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_audio_token": 0.000002, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_200k_tokens": 0.000018, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": false, - "supports_assistant_prefill": true + "supports_web_search": true }, - "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 6e-8, - "output_cost_per_token": 4e-7, - "cache_creation_input_token_cost": 0, - "cache_read_input_token_cost": 1e-8, + "openrouter/~moonshotai/kimi-latest": { + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.0000014989, "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 1048576, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", + "output_cost_per_token": 0.000010758, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": false + "supports_web_search": false }, - "openrouter/z-ai/glm-5": { - "input_cost_per_token": 6e-7, + "openrouter/~openai/gpt-astra-latest": { + "cache_creation_input_token_cost": 0.0000125, + "cache_creation_input_token_cost_above_272k_tokens": 0.000025, + "cache_read_input_token_cost": 0.000001, + "cache_read_input_token_cost_above_272k_tokens": 0.000002, + "input_cost_per_token": 0.00001, + "input_cost_per_token_above_272k_tokens": 0.00002, "litellm_provider": "openrouter", - "max_input_tokens": 202752, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.00000192, - "source": "https://openrouter.ai/z-ai/glm-5", + "output_cost_per_token": 0.00005, + "output_cost_per_token_above_272k_tokens": 0.000075, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5-turbo": { - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.000004, - "cache_read_input_token_cost": 2.4e-7, + "openrouter/~openai/gpt-luna-latest": { + "cache_creation_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, + "cache_read_input_token_cost": 1e-8, + "cache_read_input_token_cost_above_272k_tokens": 2e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_272k_tokens": 2e-7, "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5-turbo", + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_272k_tokens": 7.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 9.66e-7, - "output_cost_per_token": 0.000003036, - "cache_read_input_token_cost": 1.794e-7, - "cache_creation_input_token_cost": 0, + "openrouter/~openai/gpt-mini-latest": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 7.5e-7, "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.1", + "output_cost_per_token": 0.0000045, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 9.66e-7, - "output_cost_per_token": 0.000003036, - "cache_read_input_token_cost": 1.932e-7, + "openrouter/~openai/gpt-sol-latest": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.2", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_272k_tokens": 0.000015, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5.2:free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "openrouter/~openai/gpt-terra-latest": { + "cache_creation_input_token_cost": 0.0000025, + "cache_creation_input_token_cost_above_272k_tokens": 0.000005, + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_272k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_272k_tokens": 0.000004, "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.2:free", + "output_cost_per_token": 0.000012, + "output_cost_per_token_above_272k_tokens": 0.000018, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": false + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 0.0000014, - "output_cost_per_token": 0.0000044, - "cache_read_input_token_cost": 1.4e-7, + "openrouter/~x-ai/grok-latest": { + "cache_read_input_token_cost": 4e-7, + "cache_read_input_token_cost_above_200k_tokens": 8e-7, + "input_cost_per_token": 0.0000016, + "input_cost_per_token_above_200k_tokens": 0.0000032, "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_input_tokens": 500000, + "max_output_tokens": 450000, + "max_tokens": 450000, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.3", + "output_cost_per_token": 0.0000048, + "output_cost_per_token_above_200k_tokens": 0.0000096, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 7.5e-8, - "output_cost_per_token": 2.5e-7, + "openrouter/~z-ai/glm-flash-latest": { "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 7.5e-8, "litellm_provider": "openrouter", "max_input_tokens": 1310720, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5.3-flash", + "output_cost_per_token": 2.5e-7, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_tool_choice": true, "supports_vision": true, - "supports_prompt_caching": true + "supports_web_search": false }, - "openrouter/z-ai/glm-5v-turbo": { - "input_cost_per_token": 0.0000012, - "output_cost_per_token": 0.000004, - "cache_read_input_token_cost": 2.4e-7, + "openrouter/~z-ai/glm-latest": { + "cache_read_input_token_cost": 1.2142e-7, + "input_cost_per_token": 6.538e-7, "litellm_provider": "openrouter", - "max_input_tokens": 202752, + "max_input_tokens": 1310720, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://openrouter.ai/z-ai/glm-5v-turbo", + "output_cost_per_token": 0.0000020548, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, "supports_function_calling": true, - "supports_tool_choice": true, + "supports_pdf_input": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true + "supports_tool_choice": true, + "supports_vision": false, + "supports_web_search": false }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-7, @@ -42308,40 +49170,50 @@ "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 0.0000012, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.5e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.0000012, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": true, + "supports_vision": false }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 0.00000266, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, "supports_vision": true, - "supports_native_structured_output": true + "supports_native_structured_output": true, + "supports_response_schema": false }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-8, @@ -43233,6 +50105,26 @@ } ] }, + "qwen_ai_platform/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-7, + "cache_read_input_token_cost": 1.6e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-7, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "qwen_ai_platform/qwen3.8-max": { "cache_read_input_token_cost": 2.5e-7, "input_cost_per_token": 0.000002, @@ -43250,6 +50142,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "qwen_ai_platform/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-7, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "qwen_ai_platform/qwq-plus": { "input_cost_per_token": 8e-7, "litellm_provider": "qwen_ai_platform", @@ -44300,29 +51212,35 @@ "supports_system_messages": true }, "replicate/google/gemini-2.5-flash": { - "input_cost_per_token": 0.0000025, + "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "litellm_provider": "replicate", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_image_size": false + "supports_tool_choice": false, + "supports_response_schema": false, + "supports_image_size": false, + "supports_reasoning": true, + "supports_video_input": true }, "replicate/google/gemini-3-pro": { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "litellm_provider": "replicate", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "supports_function_calling": false, + "supports_parallel_function_calling": false, "supports_vision": true, "supports_system_messages": true, - "supports_tool_choice": true, - "supports_response_schema": true + "supports_tool_choice": false, + "supports_response_schema": false, + "input_cost_per_token_above_200k_tokens": 0.000004, + "output_cost_per_token_above_200k_tokens": 0.000018, + "supports_audio_input": true, + "supports_video_input": true }, "replicate/ibm-granite/granite-3.3-8b-instruct": { "input_cost_per_token": 3e-8, @@ -44648,31 +51566,6 @@ "output_cost_per_token": 0.000007, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "deprecation_date": "2026-03-20", - "input_cost_per_token": 7e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0000014, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 0.000003, - "litellm_provider": "sambanova", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0000045, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/DeepSeek-V3.1": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -44715,73 +51608,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 4e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - }, - "mode": "chat", - "output_cost_per_token": 7e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 0.000005, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.00001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "deprecation_date": "2026-04-14", - "input_cost_per_token": 1e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 4e-8, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8e-8, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 8e-8, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.6e-7, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, "sambanova/Meta-Llama-3.3-70B-Instruct": { "input_cost_per_token": 6e-7, "litellm_provider": "sambanova", @@ -44795,17 +51621,6 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "sambanova/Meta-Llama-Guard-3-8B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 3e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, "sambanova/MiniMax-M2.7": { "input_cost_per_token": 6e-7, "litellm_provider": "sambanova", @@ -44819,43 +51634,6 @@ "supports_reasoning": true, "supports_tool_choice": true }, - "sambanova/QwQ-32B": { - "deprecation_date": "2025-06-25", - "input_cost_per_token": 5e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000001, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "deprecation_date": "2025-06-19", - "input_cost_per_token": 5e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0001, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_audio_input": true - }, - "sambanova/Qwen3-32B": { - "deprecation_date": "2026-04-06", - "input_cost_per_token": 4e-7, - "litellm_provider": "sambanova", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8e-7, - "source": "https://cloud.sambanova.ai/plans/pricing", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, "sambanova/gemma-4-31B-it": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -44921,18 +51699,6 @@ "supports_reasoning": true, "supports_vision": false }, - "scaleway/google/gemma-3-27b-it": { - "input_cost_per_token": 2.5e-7, - "litellm_provider": "scaleway", - "max_input_tokens": 40000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 5e-7, - "supports_function_calling": true, - "supports_vision": true, - "deprecation_date": "2026-08-01" - }, "scaleway/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 2.5e-7, "litellm_provider": "scaleway", @@ -44945,18 +51711,6 @@ "supports_reasoning": true, "supports_vision": true }, - "scaleway/hcompany/holo2-30b-a3b": { - "input_cost_per_token": 3e-7, - "litellm_provider": "scaleway", - "max_input_tokens": 22000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-7, - "supports_reasoning": true, - "supports_vision": true, - "deprecation_date": "2026-08-09" - }, "scaleway/meta/llama-3.3-70b-instruct": { "input_cost_per_token": 9e-7, "litellm_provider": "scaleway", @@ -44967,17 +51721,6 @@ "output_cost_per_token": 9e-7, "supports_function_calling": true }, - "scaleway/mistralai/devstral-2-123b-instruct-2512": { - "input_cost_per_token": 4e-7, - "litellm_provider": "scaleway", - "max_input_tokens": 200000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 0.000002, - "supports_function_calling": true, - "deprecation_date": "2026-08-01" - }, "scaleway/mistralai/mistral-medium-3.5-128b": { "input_cost_per_token": 0.0000015, "litellm_provider": "scaleway", @@ -45014,18 +51757,6 @@ "supports_function_calling": true, "deprecation_date": "2026-10-01" }, - "scaleway/mistralai/voxtral-small-24b-2507": { - "input_cost_per_audio_token": 1.5e-7, - "input_cost_per_token": 1.5e-7, - "litellm_provider": "scaleway", - "max_input_tokens": 32000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3.5e-7, - "supports_audio_input": true, - "deprecation_date": "2026-08-01" - }, "scaleway/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-7, "litellm_provider": "scaleway", @@ -45753,6 +52484,15 @@ "mode": "chat", "output_cost_per_token": 1e-7 }, + "together_ai/MiniMaxAI/MiniMax-M2.7": { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000012, + "cache_read_input_token_cost": 6e-8, + "litellm_provider": "together_ai", + "max_input_tokens": 196608, + "mode": "chat", + "source": "https://api.together.ai/v1/models" + }, "together_ai/MiniMaxAI/MiniMax-M3": { "cache_read_input_token_cost": 6e-8, "input_cost_per_token": 3e-7, @@ -45761,7 +52501,7 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 0.0000012, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -45779,120 +52519,38 @@ "output_cost_per_token": 0, "source": "https://docs.together.ai/docs/serverless-models" }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "deprecation_date": "2026-07-10", - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262000, - "mode": "chat", - "output_cost_per_token": 0.000006, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 40000, - "mode": "chat", - "output_cost_per_token": 6e-7, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_tool_choice": false - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "deprecation_date": "2026-06-04", - "input_cost_per_token": 0.000002, + "together_ai/Qwen/Qwen2-1.5B-Instruct": { + "input_cost_per_token": 2e-8, "litellm_provider": "together_ai", - "max_input_tokens": 256000, "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 2e-8, + "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 1.5e-7, + "together_ai/Qwen/Qwen2.5-14B-Instruct": { + "input_cost_per_token": 8e-7, "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.7-Plus" - }, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 8e-7, + "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 1.5e-7, + "together_ai/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 0.0000012, "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/Qwen/Qwen3.6-Plus" - }, "mode": "chat", - "output_cost_per_token": 0.0000015, - "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 0.0000012, + "source": "https://api.together.ai/v1/models" }, - "together_ai/Qwen/Qwen3.5-397B-A17B": { - "cache_read_input_token_cost": 3.5e-7, - "deprecation_date": "2026-06-29", - "input_cost_per_token": 6e-7, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { "litellm_provider": "together_ai", - "max_input_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.0000036, - "source": "https://www.together.ai/models/qwen3-5-397b-a17b", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 3e-7, + "max_input_tokens": 32768, + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.5-9B": { "input_cost_per_token": 1.7e-7, @@ -45901,7 +52559,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-7, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -45916,18 +52574,18 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.000003, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.0000025, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.0000015, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 0.0000075, - "source": "https://docs.together.ai/docs/serverless-models", + "output_cost_per_token": 0.0000045, + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { @@ -45937,7 +52595,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.00000128, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { "cache_read_input_token_cost": 2.5e-7, @@ -45947,17 +52605,24 @@ "max_tokens": 1010000, "mode": "chat", "output_cost_per_token": 0.000006, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.8-Flash": { - "input_cost_per_token": 1.5e-7, + "input_cost_per_token": 9e-8, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 4.7e-7, - "source": "https://docs.together.ai/docs/serverless-models" + "output_cost_per_token": 2.82e-7, + "source": "https://api.together.ai/v1/models" + }, + "together_ai/arcee-ai/trinity-mini": { + "input_cost_per_token": 4.5e-8, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://api.together.ai/v1/models" }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-7, @@ -45966,37 +52631,15 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-7, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "deprecation_date": "2026-05-14", + "together_ai/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 0.000003, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "max_tokens": 20480, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", "output_cost_per_token": 0.000007, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "deprecation_date": "2026-02-03", - "input_cost_per_token": 5.5e-7, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "mode": "chat", - "output_cost_per_token": 0.00000219, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3": { "input_cost_per_token": 0.00000125, @@ -46014,103 +52657,72 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "deprecation_date": "2026-05-14", - "input_cost_per_token": 6e-7, - "litellm_provider": "together_ai", - "max_tokens": 16384, - "metadata": { - "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" - }, - "mode": "chat", - "output_cost_per_token": 0.0000017, - "source": "https://www.together.ai/models/deepseek-v3-1", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 16384 - }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-8, + "deprecation_date": "2026-09-29", "input_cost_per_token": 1.4e-7, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-7, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V4-Pro": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 0.00000174, + "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.3e-7, + "deprecation_date": "2026-09-29", + "input_cost_per_token": 0.00000132, "litellm_provider": "together_ai", - "max_input_tokens": 512000, - "max_tokens": 512000, + "max_input_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 0.00000348, - "source": "https://docs.together.ai/docs/serverless-models", + "output_cost_per_token": 0.00000396, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { - "cache_read_input_token_cost": 1.3e-7, - "input_cost_per_token": 0.00000132, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-9, + "input_cost_per_token": 3e-7, "litellm_provider": "together_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 0.00000396, - "source": "https://docs.together.ai/docs/serverless-models", + "output_cost_per_token": 0.0000012, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/google/gemma-3n-E4B-it": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 6e-8, + "together_ai/meta-llama/Llama-3.1-405B-Instruct": { + "input_cost_per_token": 0.0000035, "litellm_provider": "together_ai", - "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 1.2e-7, - "source": "https://docs.together.ai/docs/serverless-models" + "output_cost_per_token": 0.0000035, + "source": "https://api.together.ai/v1/models" }, - "together_ai/google/gemma-4-31B-it": { - "input_cost_per_token": 3.9e-7, + "together_ai/meta-llama/Llama-3.2-1B-Instruct": { + "input_cost_per_token": 6e-8, "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 9.7e-7, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "output_cost_per_token": 6e-8, + "source": "https://api.together.ai/v1/models" }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", + "together_ai/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 6e-8, "litellm_provider": "together_ai", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "output_cost_per_token": 6e-8, + "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "input_cost_per_token": 0.00000104, @@ -46119,83 +52731,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.00000104, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { - "deprecation_date": "2025-11-13", - "input_cost_per_token": 0, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 0, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "deprecation_date": "2026-03-31", - "input_cost_per_token": 2.7e-7, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.5e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 1.8e-7, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 5.9e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-Guard-4-12B": { - "deprecation_date": "2026-08-25", - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 1048576, - "max_tokens": 1048576, - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://docs.together.ai/docs/serverless-models" - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "deprecation_date": "2026-02-06", - "input_cost_per_token": 0.0000035, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 0.0000035, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "deprecation_date": "2026-02-25", - "input_cost_per_token": 8.8e-7, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 8.8e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 1.8e-7, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.8e-7, + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -46209,36 +52745,24 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0000015, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "deprecation_date": "2025-11-13", - "litellm_provider": "together_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "deprecation_date": "2026-04-02", + "together_ai/mistralai/Ministral-3-14B-Instruct-2512": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "together_ai", + "max_input_tokens": 262144, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true + "source": "https://api.together.ai/v1/models" }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "deprecation_date": "2026-04-16", - "input_cost_per_token": 6e-7, + "together_ai/mistralai/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, "litellm_provider": "together_ai", + "max_input_tokens": 32768, "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2-Instruct": { "input_cost_per_token": 0.000001, @@ -46254,54 +52778,13 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/moonshotai/Kimi-K2-Instruct-0905": { - "deprecation_date": "2026-03-06", - "input_cost_per_token": 0.000001, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", - "output_cost_per_token": 0.000003, - "source": "https://www.together.ai/models/kimi-k2-0905", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "together_ai/moonshotai/Kimi-K2.5": { - "deprecation_date": "2026-05-21", + "together_ai/moonshotai/Kimi-K2.5-fp4": { "input_cost_per_token": 5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 256000, - "max_tokens": 256000, - "metadata": { - "successor": "together_ai/moonshotai/Kimi-K3" - }, - "mode": "chat", "output_cost_per_token": 0.0000028, - "source": "https://www.together.ai/models/kimi-k2-5", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_reasoning": true - }, - "together_ai/moonshotai/Kimi-K2.7-Code": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 1.9e-7, - "input_cost_per_token": 9.5e-7, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 0.000004, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-7, @@ -46316,7 +52799,7 @@ "high", "max" ], - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46325,22 +52808,13 @@ "supports_tool_choice": true, "supports_vision": true }, - "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { - "deprecation_date": "2026-08-27", - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 6e-7, + "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2.5e-7, "litellm_provider": "together_ai", - "max_input_tokens": 512288, - "max_tokens": 512288, + "max_input_tokens": 131072, "mode": "chat", - "output_cost_per_token": 0.0000036, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true + "source": "https://api.together.ai/v1/models" }, "together_ai/openai/gpt-oss-120b": { "input_cost_per_token": 1.5e-7, @@ -46349,35 +52823,13 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-7, - "source": "https://www.together.ai/models/gpt-oss-120b", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/openai/gpt-oss-20b": { - "input_cost_per_token": 5e-8, - "litellm_provider": "together_ai", - "max_input_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-7, - "source": "https://www.together.ai/models/gpt-oss-20b", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "together_ai/pearl-ai/gemma-4-31b-it": { - "deprecation_date": "2026-08-27", - "input_cost_per_token": 2.8e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 8.6e-7, - "source": "https://docs.together.ai/docs/serverless-models" - }, "together_ai/thinkingmachines/Inkling": { "cache_read_input_token_cost": 1.7e-7, "input_cost_per_token": 0.000001, @@ -46386,24 +52838,13 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 0.00000405, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, - "together_ai/thinkingmachines/Inkling-Small": { - "cache_read_input_token_cost": 1e-7, - "input_cost_per_token": 5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 524288, - "max_tokens": 524288, - "mode": "chat", - "output_cost_per_token": 0.0000012, - "source": "https://docs.together.ai/docs/serverless-models", - "supports_prompt_caching": true - }, "together_ai/togethercomputer/CodeLlama-34b-Instruct": { "litellm_provider": "together_ai", "mode": "chat", @@ -46411,47 +52852,17 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 2e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0000011, - "source": "https://www.together.ai/models/glm-4-5-air", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, "together_ai/zai-org/GLM-4.6": { "input_cost_per_token": 6e-7, "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_tokens": 200000, + "max_input_tokens": 202752, + "max_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, "mode": "chat", "output_cost_per_token": 0.0000022, - "source": "https://www.together.ai/models/glm-4-6", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "together_ai/zai-org/GLM-4.7": { - "deprecation_date": "2026-04-02", - "input_cost_per_token": 4.5e-7, - "litellm_provider": "together_ai", - "max_input_tokens": 200000, - "max_tokens": 200000, - "metadata": { - "successor": "together_ai/zai-org/GLM-5.2" - }, - "mode": "chat", - "output_cost_per_token": 0.000002, - "source": "https://www.together.ai/models/glm-4-7", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -46466,7 +52877,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46483,7 +52894,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.0000044, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46500,7 +52911,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-7, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -46516,23 +52927,6 @@ "mode": "chat", "supports_video_input": true }, - "us-gov.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 3e-7, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.0000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-8, - "cache_creation_input_token_cost": 3.75e-7 - }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 0.000015, "cache_creation_input_token_cost_above_1hr": 0.000024, @@ -46564,7 +52958,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -46574,12 +52969,14 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -46605,12 +53002,14 @@ "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00003, "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -46629,6 +53028,41 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true }, + "us-gov.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 0.000006, + "cache_creation_input_token_cost_above_1hr": 0.0000096, + "cache_read_input_token_cost": 2.4e-7, + "input_cost_per_token": 0.0000048, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false + }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 0.0000045, "cache_creation_input_token_cost_above_1hr": 0.0000072, @@ -46667,12 +53101,14 @@ "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000024, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.000012, "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -46820,6 +53256,7 @@ "supports_vision": true }, "us.amazon.nova-lite-v1:0": { + "cache_read_input_token_cost": 1.5e-8, "input_cost_per_token": 6e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -46835,6 +53272,7 @@ "supports_tool_choice": true }, "us.amazon.nova-micro-v1:0": { + "cache_read_input_token_cost": 8.75e-9, "input_cost_per_token": 3.5e-8, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -46847,22 +53285,8 @@ "supports_response_schema": true, "supports_tool_choice": true }, - "us.amazon.nova-premier-v1:0": { - "deprecation_date": "2026-09-14", - "input_cost_per_token": 0.0000025, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "max_tokens": 10000, - "mode": "chat", - "output_cost_per_token": 0.0000125, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_vision": true - }, "us.amazon.nova-pro-v1:0": { + "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, @@ -46950,23 +53374,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "deprecation_date": "2026-09-10", - "input_cost_per_token": 2.5e-7, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.00000125, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 2.5e-8, - "cache_creation_input_token_cost": 3.125e-7 - }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 0.000015, "litellm_provider": "bedrock", @@ -46982,23 +53389,6 @@ "cache_read_input_token_cost": 0.0000015, "cache_creation_input_token_cost": 0.00001875 }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "deprecation_date": "2026-07-30", - "input_cost_per_token": 0.000003, - "litellm_provider": "bedrock", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 3e-7, - "cache_creation_input_token_cost": 0.00000375 - }, "us.anthropic.claude-fable-5": { "cache_creation_input_token_cost": 0.00001375, "cache_creation_input_token_cost_above_1hr": 0.000022, @@ -47034,7 +53424,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 0.00001375, @@ -47072,7 +53463,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 0.000001375, @@ -47257,7 +53649,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -47268,6 +53661,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -47294,7 +53688,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -47305,6 +53700,7 @@ "cache_read_input_token_cost": 5.5e-7, "input_cost_per_token": 0.0000055, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -47330,7 +53726,48 @@ "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "us.anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 0.0000055, + "cache_creation_input_token_cost_above_1hr": 0.0000088, + "cache_read_input_token_cost": 2.2e-7, + "input_cost_per_token": 0.0000044, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000022, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "thinking_always_on": true, + "supports_forced_tool_use": false }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 0.00000375, @@ -47433,7 +53870,8 @@ "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -47442,6 +53880,7 @@ "cache_read_input_token_cost": 2.2e-7, "input_cost_per_token": 0.0000022, "litellm_provider": "bedrock_converse", + "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -47470,7 +53909,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://aws.amazon.com/bedrock/pricing/" }, "us.deepseek.r1-v1:0": { "input_cost_per_token": 0.00000135, @@ -47640,6 +54080,26 @@ "supports_function_calling": true, "supports_tool_choice": false }, + "us.moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "us.openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-7, "input_cost_per_token_above_272k_tokens": 4.4e-7, @@ -47662,8 +54122,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "us.openai.gpt-5.6-sol": { @@ -47688,8 +54151,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "us.openai.gpt-5.6-terra": { @@ -47714,8 +54180,11 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true }, "us.openai.gpt-6-astra": { @@ -47740,9 +54209,13 @@ "text" ], "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true, "supports_vision": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html" }, @@ -48301,34 +54774,6 @@ "output_cost_per_token": 9e-7, "supports_tool_choice": true }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 1.5e-7, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-7, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-06-01", - "input_cost_per_token": 7.5e-8, - "litellm_provider": "vercel_ai_gateway", - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 3e-7, - "supports_vision": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, "vercel_ai_gateway/google/gemini-2.5-flash": { "input_cost_per_token": 3e-7, "litellm_provider": "vercel_ai_gateway", @@ -48341,10 +54786,15 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_response_schema": true, - "supports_image_size": false + "supports_image_size": false, + "cache_read_input_token_cost": 3e-8, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_web_search": true, + "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemini-2.5-pro": { - "input_cost_per_token": 0.0000025, + "input_cost_per_token": 0.00000125, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -48354,7 +54804,15 @@ "supports_vision": true, "supports_function_calling": true, "supports_tool_choice": true, - "supports_response_schema": true + "supports_response_schema": true, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "output_cost_per_token_above_200k_tokens": 0.000015, + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, + "supports_reasoning": true, + "supports_pdf_input": true, + "supports_web_search": true, + "supports_prompt_caching": true }, "vercel_ai_gateway/google/gemma-2-9b": { "input_cost_per_token": 2e-7, @@ -49072,28 +55530,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "deprecation_date": "2026-05-11", - "input_cost_per_token": 0.000003, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.000015, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-3-haiku": { "input_cost_per_token": 2.5e-7, "litellm_provider": "vertex_ai-anthropic_models", @@ -49366,72 +55802,6 @@ "supports_vision": true, "prompt_cache_min_tokens": 4096 }, - "vertex_ai/claude-opus-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, - "vertex_ai/claude-opus-4-1": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "input_cost_per_token_batches": 0.0000075, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "output_cost_per_token_batches": 0.0000375, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "deprecation_date": "2026-08-05", - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, - "input_cost_per_token_batches": 0.0000075, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 0.000075, - "output_cost_per_token_batches": 0.0000375, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, "vertex_ai/claude-opus-4-5": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 0.00000625, @@ -49693,57 +56063,65 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024 }, - "vertex_ai/claude-opus-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 0.00001875, - "cache_creation_input_token_cost_above_1hr": 0.00003, - "cache_read_input_token_cost": 0.0000015, - "input_cost_per_token": 0.000015, + "vertex_ai/claude-opus-5": { + "deprecation_date": "2027-01-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000075, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 }, - "vertex_ai/claude-opus-5": { - "deprecation_date": "2027-01-24", + "vertex_ai/claude-opus-5-5": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, + "output_cost_per_token": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49755,29 +56133,31 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512 }, - "vertex_ai/claude-opus-5@default": { - "deprecation_date": "2027-01-24", + "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 0.00000625, - "cache_creation_input_token_cost_above_1hr": 0.00001, - "cache_read_input_token_cost": 5e-7, - "input_cost_per_token": 0.000005, + "cache_creation_input_token_cost": 0.000005, + "cache_creation_input_token_cost_above_1hr": 0.000008, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 0.000004, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000025, + "output_cost_per_token": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, + "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, + "supports_forced_tool_use": false, "supports_function_calling": true, + "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49789,37 +56169,39 @@ "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512 }, - "vertex_ai/claude-sonnet-4": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "vertex_ai/claude-opus-5@default": { + "deprecation_date": "2027-01-24", + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "supports_adaptive_thinking": true, + "cache_creation_input_token_cost": 0.00000625, + "cache_creation_input_token_cost_above_1hr": 0.00001, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000005, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000015, + "output_cost_per_token": 0.000025, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "prompt_cache_min_tokens": 512 }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", @@ -49946,38 +56328,6 @@ "supports_output_config": true, "prompt_cache_min_tokens": 1024 }, - "vertex_ai/claude-sonnet-4@20250514": { - "deprecation_date": "2026-05-14", - "cache_creation_input_token_cost": 0.00000375, - "cache_creation_input_token_cost_above_1hr": 0.000006, - "cache_read_input_token_cost": 3e-7, - "input_cost_per_token": 0.000003, - "input_cost_per_token_above_200k_tokens": 0.000006, - "output_cost_per_token_above_200k_tokens": 0.0000225, - "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, - "cache_read_input_token_cost_above_200k_tokens": 6e-7, - "litellm_provider": "vertex_ai-anthropic_models", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.000015, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024 - }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", "regional_endpoint_uplift_multiplier": 1.1, @@ -50162,6 +56512,9 @@ "cache_read_input_token_cost": 3e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token": 3e-7, + "input_cost_per_token_batches": 1.5e-7, + "input_cost_per_token_flex": 1.5e-7, + "input_cost_per_token_priority": 5.4e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, @@ -50171,8 +56524,10 @@ "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token": 0.0000025, + "output_cost_per_token_batches": 0.00000125, + "output_cost_per_token_flex": 0.00000125, "rpm": 100000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50204,7 +56559,9 @@ "supports_image_size": false }, "vertex_ai/gemini-3-flash-preview": { + "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost": 5e-8, + "cache_read_input_token_cost_flex": 5e-8, "input_cost_per_token": 5e-7, "input_cost_per_audio_token": 0.000001, "litellm_provider": "vertex_ai", @@ -50213,7 +56570,7 @@ "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 0.000003, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50250,7 +56607,12 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 5e-7, + "input_cost_per_token_batches": 2.5e-7, + "input_cost_per_token_flex": 2.5e-7, + "output_cost_per_token_batches": 0.0000015, + "output_cost_per_token_flex": 0.0000015 }, "vertex_ai/gemini-3-pro-preview": { "cache_read_input_token_cost": 2e-7, @@ -50308,8 +56670,10 @@ "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-flash-lite": { + "cache_read_input_audio_token_cost": 5e-8, "deprecation_date": "2027-05-07", "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, @@ -50328,7 +56692,7 @@ "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50364,13 +56728,17 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token_batches": 2.5e-7 }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_batches": 1.25e-8, + "cache_read_input_token_cost_flex": 1.25e-8, "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-7, "input_cost_per_token_batches": 1.25e-7, + "input_cost_per_token_flex": 1.25e-7, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -50380,6 +56748,7 @@ "output_cost_per_image_token": 0.00003, "output_cost_per_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, + "output_cost_per_token_flex": 7.5e-7, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -50470,7 +56839,7 @@ "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50504,13 +56873,16 @@ "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, + "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token_flex": 0.000001, + "output_cost_per_token_flex": 0.000006 }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -50575,6 +56947,7 @@ "prompt_cache_min_tokens": 4096, "deprecation_date": "2027-05-19", "cache_read_input_token_cost": 1.5e-7, + "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_token": 0.0000015, "input_cost_per_audio_token": 0.0000015, "litellm_provider": "vertex_ai", @@ -50585,7 +56958,7 @@ "output_cost_per_reasoning_token": 0.000009, "output_cost_per_token": 0.000009, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50634,8 +57007,9 @@ "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", "cache_read_input_token_cost": 3e-8, + "cache_read_input_token_cost_batches": 1.5e-8, "cache_read_input_token_cost_flex": 1.5e-8, - "cache_read_input_token_cost_priority": 5e-8, + "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_token": 3e-7, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, @@ -50651,7 +57025,7 @@ "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50692,6 +57066,7 @@ "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -50706,7 +57081,7 @@ "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50749,6 +57124,7 @@ "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -50763,7 +57139,7 @@ "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50784,6 +57160,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -50806,6 +57183,7 @@ "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token": 7.5e-7, "input_cost_per_token_batches": 3.75e-7, @@ -50820,7 +57198,7 @@ "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -50841,6 +57219,7 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_minimal_reasoning_effort": false, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, @@ -50860,10 +57239,25 @@ "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, + "vertex_ai/gemini-omni-1.1-flash": { + "input_cost_per_token": 0.0000015, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 0.000009, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemma-4-26b-a4b-it": { + "cache_read_input_token_cost": 1.5e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, "vertex_ai/google/gemma-4-26b-a4b-it-maas": { "input_cost_per_token": 1.5e-7, "litellm_provider": "vertex_ai-openai_models", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -51198,27 +57592,29 @@ "supports_tool_choice": true }, "vertex_ai/mistral-small-2503": { - "input_cost_per_token": 0.000001, + "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 3e-7, "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/mistral-small-2503@001": { - "input_cost_per_token": 0.000001, + "input_cost_per_token": 1e-7, "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 0.000003, + "output_cost_per_token": 3e-7, "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/mistralai/codestral-2": { "input_cost_per_token": 3e-7, @@ -51289,15 +57685,16 @@ "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { - "input_cost_per_token": 7.5e-8, + "input_cost_per_token": 7e-8, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 3e-7, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", - "supports_reasoning": true + "output_cost_per_token": 2.5e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_reasoning": true, + "cache_read_input_token_cost": 7e-9 }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { "input_cost_per_token": 2.2e-7, @@ -51371,6 +57768,7 @@ "output_cost_per_token": 5e-7, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -51387,6 +57785,7 @@ "output_cost_per_token": 5e-7, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -51407,6 +57806,7 @@ "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -51426,6 +57826,7 @@ "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -51446,6 +57847,7 @@ "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -51465,6 +57867,7 @@ "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -51656,9 +58059,42 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-7, + "input_cost_per_token": 8.625e-7, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000043125, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-8, + "input_cost_per_token": 4.3125e-7, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.00000215625, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "litellm_provider": "wandb", @@ -51666,22 +58102,10 @@ "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 197000, - "max_input_tokens": 197000, - "max_output_tokens": 197000, - "input_cost_per_token": 3e-7, - "output_cost_per_token": 0.0000012, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true - }, "wandb/MiniMaxAI/MiniMax-M3": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 9.6e-7, "cache_read_input_token_cost": 5e-8, @@ -51692,8 +58116,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/OpenPipe/Qwen3-14B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 32768, - "max_input_tokens": 32768, + "max_input_tokens": 32800, "input_cost_per_token": 5e-8, "output_cost_per_token": 2.2e-7, "litellm_provider": "wandb", @@ -51701,27 +58126,10 @@ "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 1e-7, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "deprecation_date": "2026-10-05", "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "litellm_provider": "wandb", @@ -51729,19 +58137,11 @@ "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.0000015, - "litellm_provider": "wandb", - "mode": "chat", - "source": "https://wandb.ai/site/pricing/tokens/" - }, "wandb/Qwen/Qwen3.5-35B-A3B": { + "deprecation_date": "2026-10-05", + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "litellm_provider": "wandb", @@ -51750,11 +58150,13 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.6-27B": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "cache_read_input_token_cost": 1.2e-7, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -51762,8 +58164,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.6-35B-A3B": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "litellm_provider": "wandb", @@ -51772,8 +58175,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.8-27B": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000003, "cache_read_input_token_cost": 1.5e-7, @@ -51783,25 +58187,8 @@ "supports_vision": true, "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.00000135, - "output_cost_per_token": 0.0000054, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 161000, - "max_input_tokens": 161000, - "max_output_tokens": 161000, - "input_cost_per_token": 0.00000114, - "output_cost_per_token": 0.00000275, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/deepseek-ai/DeepSeek-V3.1": { + "supports_reasoning": true, "max_tokens": 128000, "max_input_tokens": 161000, "max_output_tokens": 128000, @@ -51812,11 +58199,13 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { + "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "cache_read_input_token_cost": 7e-8, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -51824,8 +58213,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 2.8e-7, "cache_read_input_token_cost": 7e-8, @@ -51836,20 +58226,34 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { + "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 0.00000115, "output_cost_per_token": 0.00000255, "cache_read_input_token_cost": 2e-7, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, + "wandb/deepseek-ai/DeepSeek-V4-Pro-0813": { + "litellm_provider": "wandb", + "mode": "chat", + "supports_reasoning": true, + "input_cost_per_token": 0.00000131, + "output_cost_per_token": 0.00000396, + "cache_read_input_token_cost": 4.4e-8, + "max_input_tokens": 1049000, + "supports_prompt_caching": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, "wandb/google/gemma-4-31B-it": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-7, "output_cost_per_token": 3.4e-7, "litellm_provider": "wandb", @@ -51858,8 +58262,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/ibm-granite/granite-4.1-8b": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "litellm_provider": "wandb", @@ -51867,9 +58272,21 @@ "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, + "wandb/ibm-granite/granite-4.2-8b": { + "litellm_provider": "wandb", + "mode": "chat", + "supports_reasoning": true, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1.5e-7, + "cache_read_input_token_cost": 5e-8, + "max_input_tokens": 131000, + "supports_prompt_caching": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "litellm_provider": "wandb", @@ -51879,7 +58296,7 @@ }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 2.2e-7, @@ -51897,33 +58314,6 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 64000, - "max_input_tokens": 64000, - "max_output_tokens": 64000, - "input_cost_per_token": 1.7e-7, - "output_cost_per_token": 6.6e-7, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/microsoft/Phi-4-mini-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 0.008, - "output_cost_per_token": 0.035, - "litellm_provider": "wandb", - "mode": "chat" - }, - "wandb/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 6e-7, - "output_cost_per_token": 0.0000025, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/moonshotai/Kimi-K2.5": { "max_tokens": 262144, "max_input_tokens": 262144, @@ -51940,8 +58330,9 @@ "supports_vision": true }, "wandb/moonshotai/Kimi-K2.6": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000341, "cache_read_input_token_cost": 1.5e-7, @@ -51952,8 +58343,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.7-Code": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 0.0000035, "cache_read_input_token_cost": 1.5e-7, @@ -51964,11 +58356,12 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 7.5e-7, - "output_cost_per_token": 0.00000275, - "cache_read_input_token_cost": 1.5e-7, + "max_input_tokens": 262000, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.00000215, + "cache_read_input_token_cost": 1e-7, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -51976,11 +58369,12 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 1e-7, - "output_cost_per_token": 2.5e-7, - "cache_read_input_token_cost": 5e-8, + "max_input_tokens": 262000, + "input_cost_per_token": 7e-8, + "output_cost_per_token": 2e-7, + "cache_read_input_token_cost": 4e-8, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -51988,8 +58382,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-120b": { + "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-8, "output_cost_per_token": 1.7e-7, @@ -51998,8 +58393,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-20b": { + "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-8, "output_cost_per_token": 1.3e-7, @@ -52007,18 +58403,10 @@ "mode": "chat", "source": "https://wandb.ai/site/pricing/tokens/" }, - "wandb/zai-org/GLM-4.5": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.2, - "litellm_provider": "wandb", - "mode": "chat" - }, "wandb/zai-org/GLM-5.2": { + "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 1049000, "input_cost_per_token": 7.6e-7, "output_cost_per_token": 0.00000242, "cache_read_input_token_cost": 1.4e-7, @@ -52028,6 +58416,20 @@ "supports_vision": false, "source": "https://wandb.ai/site/pricing/tokens/" }, + "wandb/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 1.5e-7, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://wandb.ai/site/pricing/tokens/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "watsonx/bigscience/mt0-xxl": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -52408,6 +58810,17 @@ "supports_parallel_function_calling": false, "supports_vision": false }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-7, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "writer.palmyra-x4-v1:0": { "input_cost_per_token": 0.0000025, "litellm_provider": "bedrock_converse", @@ -52509,441 +58922,354 @@ "supports_vision": true, "supports_web_search": true }, - "xai/grok-3": { + "xai/grok-4.20": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, + "supports_reasoning": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 - }, - "xai/grok-3-beta": { - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "supports_response_schema": true }, - "xai/grok-3-fast-beta": { + "xai/grok-4.20-0309": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": false, + "supports_reasoning": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 - }, - "xai/grok-3-fast-latest": { - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token": 0.00000125, - "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", - "supports_function_calling": true, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "supports_response_schema": true }, - "xai/grok-3-latest": { + "xai/grok-4.20-0309-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-3-mini": { + "xai/grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-7, - "deprecation_date": "2026-02-28", "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-3-mini-beta": { + "xai/grok-4.20-beta": { "cache_read_input_token_cost": 2e-7, - "deprecation_date": "2026-02-28", "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-3-mini-fast": { + "xai/grok-4.20-beta-0309": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-02-28", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-3-mini-fast-beta": { + "xai/grok-4.20-beta-0309-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-02-28", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-3-mini-fast-latest": { + "xai/grok-4.20-beta-0309-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-02-28", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-3-mini-latest": { + "xai/grok-4.20-beta-latest": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://x.ai/api#pricing", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-02-28", - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 - }, - "xai/grok-4": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, - "supports_prompt_caching": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 - }, - "xai/grok-4-0709": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "supports_response_schema": true }, - "xai/grok-4-1-fast": { + "xai/grok-4.20-beta-latest-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-4-1-fast-non-reasoning": { + "xai/grok-4.20-beta-latest-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, + "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-4-1-fast-non-reasoning-latest": { + "xai/grok-4.20-beta-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", - "supports_audio_input": true, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-4-1-fast-reasoning": { + "xai/grok-4.20-beta-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-4-1-fast-reasoning-latest": { + "xai/grok-4.20-experimental-beta-0304": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", - "supports_audio_input": true, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, + "supports_response_schema": true }, - "xai/grok-4-fast-non-reasoning": { + "xai/grok-4.20-experimental-beta-0304-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_response_schema": true }, - "xai/grok-4-fast-reasoning": { + "xai/grok-4.20-experimental-beta-0304-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", - "max_input_tokens": 2000000, - "max_output_tokens": 2000000, - "max_tokens": 2000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, + "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2026-05-15", "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 - }, - "xai/grok-4-latest": { - "input_cost_per_token": 0.00000125, - "litellm_provider": "xai", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", - "supports_function_calling": true, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_web_search": true, - "deprecation_date": "2026-05-15", - "cache_read_input_token_cost": 2e-7, - "input_cost_per_token_above_200k_tokens": 0.0000025, - "output_cost_per_token_above_200k_tokens": 0.000005, - "cache_read_input_token_cost_above_200k_tokens": 4e-7 + "supports_response_schema": true }, - "xai/grok-4.20": { + "xai/grok-4.20-experimental-beta-latest": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -52952,7 +59278,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -52961,10 +59287,11 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "supports_response_schema": true }, - "xai/grok-4.20-0309-non-reasoning": { + "xai/grok-4.20-experimental-beta-non-reasoning-latest": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -52973,7 +59300,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, @@ -52982,9 +59309,10 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_response_schema": true }, - "xai/grok-4.20-0309-reasoning": { + "xai/grok-4.20-experimental-beta-reasoning-latest": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -52993,7 +59321,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -53002,10 +59330,11 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "supports_response_schema": true }, - "xai/grok-4.20-beta-0309-non-reasoning": { + "xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -53014,7 +59343,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, @@ -53023,9 +59352,10 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_response_schema": true }, - "xai/grok-4.20-beta-0309-reasoning": { + "xai/grok-4.20-non-reasoning-gv2": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -53034,19 +59364,19 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, - "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_response_schema": true }, - "xai/grok-4.20-non-reasoning": { + "xai/grok-4.20-non-reasoning-latest": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -53055,7 +59385,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_tool_choice": true, @@ -53064,9 +59394,10 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_response_schema": true }, - "xai/grok-4.20-non-reasoning-latest": { + "xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -53075,18 +59406,20 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, - "supports_prompt_caching": true, + "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, + "supports_prompt_caching": true, "supports_response_schema": true }, - "xai/grok-4.20-reasoning": { + "xai/grok-4.20-reasoning-gv2": { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 0.00000125, "litellm_provider": "xai", @@ -53095,7 +59428,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -53104,6 +59437,7 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "supports_response_schema": true }, @@ -53116,7 +59450,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 0.0000025, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -53125,12 +59459,14 @@ "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.3": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "xai", @@ -53140,7 +59476,7 @@ "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53152,6 +59488,7 @@ "xai/grok-4.3-latest": { "cache_read_input_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.00000125, "input_cost_per_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "litellm_provider": "xai", @@ -53161,7 +59498,7 @@ "mode": "chat", "output_cost_per_token": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53173,6 +59510,7 @@ "xai/grok-4.5": { "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_image_token": 0.000002, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "xai", @@ -53182,7 +59520,7 @@ "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_above_200k_tokens": 0.000012, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53194,6 +59532,7 @@ "xai/grok-4.5-latest": { "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_image_token": 0.000002, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "xai", @@ -53203,7 +59542,7 @@ "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_above_200k_tokens": 0.000012, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53215,6 +59554,7 @@ "xai/grok-4.6": { "cache_read_input_token_cost": 5e-7, "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_image_token": 0.000002, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "xai", @@ -53224,7 +59564,29 @@ "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_above_200k_tokens": 0.000012, - "source": "https://docs.x.ai/developers/models", + "source": "https://api.x.ai/v1/language-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4.7": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_above_200k_tokens": 0.000001, + "input_cost_per_image_token": 0.000002, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "litellm_provider": "xai", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.000012, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53255,7 +59617,7 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, - "source": "https://docs.x.ai/docs/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53263,12 +59625,14 @@ "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.000001, "supports_response_schema": true, "supports_vision": true }, "xai/grok-build-latest": { "cache_read_input_token_cost": 3e-7, "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_image_token": 0.000002, "input_cost_per_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "litellm_provider": "xai", @@ -53278,7 +59642,7 @@ "mode": "chat", "output_cost_per_token": 0.000006, "output_cost_per_token_above_200k_tokens": 0.000012, - "source": "https://docs.x.ai/developers/models", + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -53289,66 +59653,66 @@ }, "xai/grok-code-fast": { "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.000001, "input_cost_per_token": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000002, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token_above_200k_tokens": 0.000004, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 0.000002, - "output_cost_per_token_above_200k_tokens": 0.000004, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15" + "supports_tool_choice": true, + "supports_vision": true }, "xai/grok-code-fast-1": { "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.000001, "input_cost_per_token": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000002, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token_above_200k_tokens": 0.000004, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 0.000002, - "output_cost_per_token_above_200k_tokens": 0.000004, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15" + "supports_tool_choice": true, + "supports_vision": true }, "xai/grok-code-fast-1-0825": { "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_image_token": 0.000001, "input_cost_per_token": 0.000001, + "input_cost_per_token_above_200k_tokens": 0.000002, "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 0.000002, - "source": "https://docs.x.ai/docs/models", + "output_cost_per_token_above_200k_tokens": 0.000004, + "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "input_cost_per_token_above_200k_tokens": 0.000002, - "output_cost_per_token_above_200k_tokens": 0.000004, - "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_response_schema": true, - "supports_vision": true, - "deprecation_date": "2026-05-15" + "supports_tool_choice": true, + "supports_vision": true }, "xai/grok-vision-beta": { "input_cost_per_image": 0.000005, @@ -53364,33 +59728,85 @@ "supports_vision": true, "supports_web_search": true }, + "xiaomi_mimo/mimo-v2.6-flash": { + "cache_read_input_token_cost": 2.8e-9, + "input_cost_per_token": 1.4e-7, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "xiaomi_mimo/mimo-v2.6-pro": { + "cache_read_input_token_cost": 3.6e-9, + "input_cost_per_token": 4.35e-7, + "litellm_provider": "xiaomi_mimo", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.7e-7, + "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, "zai.glm-4.7": { "input_cost_per_token": 6e-7, "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 203000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 0.0000022, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai.glm-4.7-flash": { "input_cost_per_token": 7e-8, "litellm_provider": "bedrock_converse", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 203000, + "max_output_tokens": 4000, + "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-7, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 0.000001, @@ -53405,7 +59821,10 @@ "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_response_schema": true, + "supports_vision": false }, "zai/glm-4-32b-0414-128k": { "input_cost_per_token": 1e-7, From d3b2566cd5d88da18e59ab8561a8a05ae9a8b53c Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 19:33:21 -0400 Subject: [PATCH 04/10] Make scrollbar styling consistent --- cecli/tui/styles.tcss | 2 +- cecli/tui/widgets/output.py | 5 +++ cecli/tui/widgets/thin_scrollbar.py | 58 +++++++++++++++++++++++++++++ tests/tui/test_output.py | 24 ++++++++++++ 4 files changed, 88 insertions(+), 1 deletion(-) create mode 100644 cecli/tui/widgets/thin_scrollbar.py create mode 100644 tests/tui/test_output.py diff --git a/cecli/tui/styles.tcss b/cecli/tui/styles.tcss index c022a4cf341..72c689bc724 100644 --- a/cecli/tui/styles.tcss +++ b/cecli/tui/styles.tcss @@ -1,5 +1,5 @@ /* - * Aider CE TUI Styles + * Cecli TUI Styles * * Uses Textual theme variables for consistent theming. * Theme defined in app.py (AIDER_THEME). diff --git a/cecli/tui/widgets/output.py b/cecli/tui/widgets/output.py index 8958591c478..33200334e0d 100644 --- a/cecli/tui/widgets/output.py +++ b/cecli/tui/widgets/output.py @@ -12,6 +12,7 @@ from textual.message import Message from .selectable_log import SelectableRichLog +from .thin_scrollbar import ThinScrollBarRenderer class CostUpdate(Message): @@ -54,6 +55,10 @@ def __init__(self, **kwargs): self.wrap = True self.can_focus = False + def on_mount(self) -> None: + """Use the compact renderer for this widget's horizontal scrollbar.""" + self.horizontal_scrollbar.renderer = ThinScrollBarRenderer + async def start_response(self): """Start a new LLM response section with streaming support.""" diff --git a/cecli/tui/widgets/thin_scrollbar.py b/cecli/tui/widgets/thin_scrollbar.py new file mode 100644 index 00000000000..bdd2033d7b7 --- /dev/null +++ b/cecli/tui/widgets/thin_scrollbar.py @@ -0,0 +1,58 @@ +"""Half-height horizontal scrollbar renderer for the TUI.""" + +from math import ceil + +from rich.color import Color +from rich.segment import Segment, Segments +from rich.style import Style as RichStyle +from textual.scrollbar import ScrollBarRender + + +class ThinScrollBarRenderer(ScrollBarRender): + """Render the horizontal scrollbar with half-block track and thumb glyphs.""" + + @classmethod + def render_bar( + cls, + size: int, + virtual_size: float, + window_size: float, + position: float, + thickness: int, + vertical: bool, + back_color: Color, + bar_color: Color, + ) -> Segments: + if vertical: + return super().render_bar( + size=size, + virtual_size=virtual_size, + window_size=window_size, + position=position, + thickness=thickness, + vertical=vertical, + back_color=back_color, + bar_color=bar_color, + ) + + if size <= 0: + return Segments([]) + + track_style = RichStyle(color=back_color, meta={"@mouse.down": "scroll_up"}) + thumb_style = RichStyle(color=bar_color, meta={"@mouse.down": "grab"}) + segments = [Segment("▄", track_style) for _ in range(size)] + + if window_size and virtual_size and window_size < virtual_size: + thumb_size = max(1, min(size, ceil(size * window_size / virtual_size))) + position_ratio = position / (virtual_size - window_size) + start = int((size - thumb_size) * position_ratio) + start = max(0, min(start, size - thumb_size)) + end = start + thumb_size + + segments[start:end] = [Segment("▄", thumb_style)] * thumb_size + for index in range(end, size): + segments[index] = Segment( + "▄", RichStyle(color=back_color, meta={"@mouse.down": "scroll_down"}) + ) + + return Segments(segments) diff --git a/tests/tui/test_output.py b/tests/tui/test_output.py new file mode 100644 index 00000000000..227e8927a92 --- /dev/null +++ b/tests/tui/test_output.py @@ -0,0 +1,24 @@ +from rich.color import Color + +from cecli.tui.widgets.thin_scrollbar import ThinScrollBarRenderer + + +def test_horizontal_scrollbar_uses_half_block_glyphs(): + track_color = Color.parse("#555555") + thumb_color = Color.parse("#00ff00") + rendered = ThinScrollBarRenderer.render_bar( + size=8, + virtual_size=16, + window_size=8, + position=0, + thickness=1, + vertical=False, + back_color=track_color, + bar_color=thumb_color, + ) + + assert [segment.text for segment in rendered.segments] == ["▄"] * 8 + assert rendered.segments[0].style.color == thumb_color + assert rendered.segments[0].style.meta["@mouse.down"] == "grab" + assert rendered.segments[4].style.color == track_color + assert rendered.segments[4].style.meta["@mouse.down"] == "scroll_down" From cddbfa792f909846aa1806b59eb141ee110f3860 Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 21:28:10 -0400 Subject: [PATCH 05/10] Change Broadcast tool formt for clarity --- cecli/tools/broadcast.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/cecli/tools/broadcast.py b/cecli/tools/broadcast.py index 17aae0056cb..8792d420728 100644 --- a/cecli/tools/broadcast.py +++ b/cecli/tools/broadcast.py @@ -226,11 +226,10 @@ def _deliver(info, message, agent_service, sender_coder): sender_name = agent_service.get_agent_name(sender_coder) or "primary" sender_uuid = str(sender_coder.uuid) message = ( - "\n" - f"[Message Sent from Agent {sender_name} ({sender_uuid})]\n" - "You may respond with the `Broadcast` tool if the message " - "is relevant to you\n\n" - f"{message}" + f"\n" + f"{message}\n\n" + "[Respond with the `Broadcast` tool to relay information " + "back to other agents as needed]\n" "" ) From d2383abec1125a597fab00f0fffe4ac116e2d491 Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 21:59:04 -0400 Subject: [PATCH 06/10] Auomatic regex mode switch for group tool --- cecli/tools/grep.py | 15 +++++++++++---- tests/tools/test_grep.py | 23 +++++++++++++++++++++++ 2 files changed, 34 insertions(+), 4 deletions(-) diff --git a/cecli/tools/grep.py b/cecli/tools/grep.py index 70b90233dc3..b1b0d2621f1 100644 --- a/cecli/tools/grep.py +++ b/cecli/tools/grep.py @@ -71,6 +71,14 @@ MAX_LINE_NUMBERS = 50 +def _should_use_regex(pattern, requested): + """Auto-enable regex for alternation unless the caller explicitly disables it.""" + if requested is False: + return False + + return bool(requested) or "|" in pattern + + def _build_exclude_args(tool_name, cmd_args): """Add exclusion arguments for common build/artifact dirs and history files.""" for exclude_dir in DEFAULT_EXCLUDE_DIRS: @@ -476,8 +484,7 @@ class Tool(BaseTool): }, "use_regex": { "type": "boolean", - "default": False, - "description": "Whether to use regex.", + "description": "Whether to use regex search or literal text.", }, "case_insensitive": { "type": "boolean", @@ -659,7 +666,7 @@ def execute( pattern = strip_hashline(search_op.get("pattern", "")) file_pattern = search_op.get("file_glob", "*") directory = search_op.get("directory", search_op.get("path", ".")) - use_regex = search_op.get("use_regex", False) + use_regex = _should_use_regex(pattern, search_op.get("use_regex")) case_insensitive = search_op.get("case_insensitive", True) mode = search_op.get("mode", "matches") @@ -1053,7 +1060,7 @@ def format_output(cls, coder, mcp_server, tool_response): pattern = search_op.get("pattern", "") file_pattern = search_op.get("file_glob", "*") directory = search_op.get("directory", search_op.get("path", ".")) - use_regex = search_op.get("use_regex", False) + use_regex = _should_use_regex(pattern, search_op.get("use_regex")) case_insensitive = search_op.get("case_insensitive", True) mode = search_op.get("mode", "matches") context_before = search_op.get("context_before", 0) diff --git a/tests/tools/test_grep.py b/tests/tools/test_grep.py index 87daa25a599..db5da5e3506 100644 --- a/tests/tools/test_grep.py +++ b/tests/tools/test_grep.py @@ -172,6 +172,29 @@ def _grep_coder(root): ) +@pytest.mark.skipif(shutil.which("rg") is None, reason="rg is required") +@pytest.mark.parametrize( + ("options", "expected_matches"), + [({}, 3), ({"use_regex": True}, 3), ({"use_regex": False}, 1)], +) +def test_pipe_pattern_uses_regex_unless_explicitly_disabled( + options, expected_matches, tmp_path, monkeypatch +): + sample = tmp_path / "sample.txt" + sample.write_text("alpha\nbeta\nalpha|beta\n") + coder = _grep_coder(tmp_path) + monkeypatch.setattr(grep.Tool, "_find_search_tool", lambda: ("rg", shutil.which("rg"))) + + search = {"pattern": "alpha|beta", "file_glob": "*.txt", "directory": "."} + search.update(options) + result = grep.Tool.execute(coder, searches=[search]) + op = result.to_dict()["result"][0] + + assert op["_"]["error"] is None + assert op["_"]["total_matches"] == expected_matches + coder.io.tool_error.assert_not_called() + + @pytest.mark.skipif(shutil.which("rg") is None, reason="rg is required") def test_matches_mode_is_compact_and_relative(tmp_path, monkeypatch): sample = tmp_path / "sample.txt" From 1649bd7a8cabd3053597c0f5dc8130c87154884b Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 22:41:16 -0400 Subject: [PATCH 07/10] Fix read file context lookup descrfiptions --- cecli/helpers/hashpos/transformations.py | 2 +- cecli/tools/read_file.py | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/cecli/helpers/hashpos/transformations.py b/cecli/helpers/hashpos/transformations.py index d481918cb90..0f76be0c164 100644 --- a/cecli/helpers/hashpos/transformations.py +++ b/cecli/helpers/hashpos/transformations.py @@ -297,7 +297,7 @@ def apply_contextual_marker( range_end: str, num_lines: int, ) -> tuple[list[int], list[int]]: - """Expand range using @C{{num}}, @P{{num}}, or @N{{num}} contextual markers. + """Expand range using @C, @P, or @N contextual markers. Requires exactly one start match. Raises ValueError when the number of start matches is not 1 (the caller is expected to format the error diff --git a/cecli/tools/read_file.py b/cecli/tools/read_file.py index 44cac9a2cf7..e7c67ebcbfe 100644 --- a/cecli/tools/read_file.py +++ b/cecli/tools/read_file.py @@ -48,8 +48,8 @@ class Tool(BaseTool): " - '@000' / '000@' for the first / last line" " - hint suffixes to disambiguate repeated patterns: ' @L' (nearest match), " " '@A{{regex}}' (closest match after the regex hit), '@B{{regex}}' (closest match before)" - " - when range_start matches one location, range_end accepts '@C{num}' (context both sides), " - " '@P{num}' (lines before the match), '@N{num}' (lines after the match)" + " - when range_start matches one location, range_end accepts '@C' (context both sides), " + " '@P' (lines before the match), '@N' (lines after the match)" "" "File edits may update prefixes of identical lines, requiring re-reading to get fresh identifiers." "" @@ -84,8 +84,8 @@ class Tool(BaseTool): "description": ( "The end of the range: an exact text pattern (up to 5 lines), '000@' for " "the last line. When range_start " - "matches one location, use '@C{num}' for context on both sides, " - "'@P{num}' for lines before the match, or '@N{num}' for lines after the match." + "matches one location, use '@C' for context on both sides, " + "'@P' for lines before the match, or '@N' for lines after the match." ), }, }, From 1c6ef610debd2a37224fa27862ad643cbd6110e2 Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 23:31:40 -0400 Subject: [PATCH 08/10] Fix unknown provider assignment --- cecli/helpers/model_config/pipeline.py | 6 ++++-- cecli/resources/providers.json | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/cecli/helpers/model_config/pipeline.py b/cecli/helpers/model_config/pipeline.py index 8e3105723b5..2839be426b2 100644 --- a/cecli/helpers/model_config/pipeline.py +++ b/cecli/helpers/model_config/pipeline.py @@ -333,7 +333,9 @@ def _closest_provider_match(sources, provider, route): Raw sources are enumerated via a lightweight top-level key scan (a string pass, never a full parse) and only ``provider/``-prefixed keys are parsed - for scoring, so the fallback stays memory friendly. + for scoring, so the fallback stays memory friendly. A candidate with no + shared leading characters is not a match: returning it would let an + unrelated route inherit an arbitrary sibling record's wire mode. """ if not provider: return None @@ -376,7 +378,7 @@ def _closest_provider_match(sources, provider, route): best_score = score best = record - return best + return best if best_score > 0 else None def _prefix_score(left, right): diff --git a/cecli/resources/providers.json b/cecli/resources/providers.json index 349b3ea9121..7f7515c6756 100644 --- a/cecli/resources/providers.json +++ b/cecli/resources/providers.json @@ -77,7 +77,8 @@ "api_key_env": [ "CHATGPT_API_KEY" ], - "display_name": "chatgpt" + "display_name": "chatgpt", + "mode": "responses" }, "chutes": { "api_base": "https://llm.chutes.ai/v1/", From 1e4c82b486ef0b7c337acb557057c30df7cf0ffe Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Tue, 22 Sep 2026 23:59:50 -0400 Subject: [PATCH 09/10] Update orchestrate tool: - Rely more strongly on explicit state for cross call data preservation - Add get_tool_schema and get_tool_signature for deeper inspection of tool call formats --- cecli/helpers/orchestration/agent_proxy.py | 17 +++ cecli/helpers/orchestration/environment.py | 6 +- cecli/helpers/orchestration/safe_methods.py | 21 ++-- cecli/helpers/orchestration/tool_proxy.py | 87 +++++++++++++++- tests/helpers/test_orchestration.py | 110 ++++++++++++++++++-- 5 files changed, 218 insertions(+), 23 deletions(-) diff --git a/cecli/helpers/orchestration/agent_proxy.py b/cecli/helpers/orchestration/agent_proxy.py index 336e9e7fd60..c753d075d43 100644 --- a/cecli/helpers/orchestration/agent_proxy.py +++ b/cecli/helpers/orchestration/agent_proxy.py @@ -89,10 +89,27 @@ def get_tool(self, tool_name: str) -> ToolProxy: self._coder, mcp_server=server, mcp_tool_name=schema_name, + tool_schema=tool_schema, ) raise ValueError(f"Unknown tool: '{tool_name}'") + def get_tool_schema(self, tool_name: str) -> dict[str, Any] | None: + """Return a copy of the full function-calling schema for a tool. + + Returns ``None`` when the tool has no schema. Unknown or disallowed + tools raise the same errors as ``get_tool``. + """ + return self.get_tool(tool_name).get_schema() + + def get_tool_signature(self, tool_name: str) -> str | None: + """Return a readable Python-style call signature for a tool. + + Optional parameters without a declared default use ``...`` to show + that they may be omitted without implying a value such as ``None``. + """ + return self.get_tool(tool_name).get_signature() + def _find_mcp_server(self, server_name: str, server_prefix: str) -> Any: if not hasattr(self._coder, "mcp_manager") or not self._coder.mcp_manager: return None diff --git a/cecli/helpers/orchestration/environment.py b/cecli/helpers/orchestration/environment.py index 0926c11665f..59cef7da459 100644 --- a/cecli/helpers/orchestration/environment.py +++ b/cecli/helpers/orchestration/environment.py @@ -547,7 +547,7 @@ def build_orchestration_context_block(agent_config: dict[str, Any]) -> str | Non context = """ The `Orchestrate` tool runs Python in a sandbox where you can script other tools programmatically. Use it for batch, loop-heavy, and repeat-able workflows. -Variables and helpers persist across calls; `state` persists across all Orchestrate calls in the session. +The sandbox is stateless between calls — variables don't persist. To carry values across calls, use `state` (per-agent) or `shared_state` (cross-agent). You may need to explore the below primitives to understand how to use the sandbox effectively. ### Primitives @@ -556,11 +556,13 @@ def build_orchestration_context_block(agent_config: dict[str, Any]) -> str | Non |-----------|--------------| | `Agent.allowed_methods()` / `Agent.allowed_tools()` | List helper methods and available tools | | `Agent.get_tool(name)` | Get a tool proxy (case-insensitive; `Local--` / `{{Server Name}}--` prefixes ok) | +| `Agent.get_tool_schema(name)` | Return a copy of the full function-calling JSON schema | +| `Agent.get_tool_signature(name)` | Return a readable Python-style signature; optional params without defaults appear as `= ...` | | `await tool.call(**params)` | Run a tool; returns `{"result": [...], "errors": [...], "details": [...]}`, items with shape `{"content", "_"}` | | `Agent.peek(result)` / `Agent.get_value(result, path, default?)` | Inspect / extract values from tool results. path is dot-separated string | | `Agent.resolve_regions(path, specs)` / `Agent.edit_region(path, edits)` | Resolve text boundaries once, then apply edits | | `gather(**tasks)` | Run tasks concurrently; results expose `.key` and `["key"]` | -| `state` / `shared_state` | Persistent dicts; `state.get(k)` falls back to `shared_state` | +| `state` / `shared_state` | Persistent dicts that survive between Orchestrate calls; `state.get(k)` falls back to `shared_state`. Use these for anything you need to reuse in a later call | | `print(...)` / `reset(local_vars=True, state=False)` | Emit output / clear namespaces | | `typeof(x)`, `isinstance(x, t)`, `hasattr(x, n)`, `repr(x)`, `vars(obj)` | Type inspection and debugging | diff --git a/cecli/helpers/orchestration/safe_methods.py b/cecli/helpers/orchestration/safe_methods.py index c7d5ea9da8c..ef54efb96bb 100644 --- a/cecli/helpers/orchestration/safe_methods.py +++ b/cecli/helpers/orchestration/safe_methods.py @@ -12,6 +12,7 @@ import pathlib import re as _re_mod import traceback as _tb_mod +from collections.abc import Mapping from typing import Any # --------------------------------------------------------------------------- @@ -139,12 +140,12 @@ async def _safe_sleep(seconds: float) -> None: await asyncio.sleep(seconds) -class GatherResult: - """Result container for named ``gather()`` calls. +class GatherResult(Mapping[str, Any]): + """Read-only mapping of named ``gather()`` task results. - Supports both attribute access (``results.my_task``) and - key access (``results["my_task"]``), plus ``len()`` and - iteration for unpacking. + Supports standard mapping access (``results["task"]``, iteration over + keys, and ``keys()``, ``values()``, and ``items()``) plus attribute access + as a convenience. Use key access when task names may collide with methods. """ def __init__(self, results: dict[str, Any]) -> None: @@ -192,7 +193,7 @@ def __len__(self) -> int: def __iter__(self): results = object.__getattribute__(self, "_results") - return iter(results.items()) + return iter(results) def keys(self) -> Any: results = object.__getattribute__(self, "_results") @@ -225,12 +226,12 @@ async def _safe_gather(*args: Any, **named_awaitables: Any): Safely execute multiple awaitables concurrently. All awaitables must be passed as keyword arguments. Results are returned - as a ``GatherResult`` with attribute and key access: + as a ``GatherResult`` mapping with attribute access as a convenience: results = await gather(read_a=task_a, grep_b=task_b) - print(results.read_a) # attribute access - print(results["grep_b"]) # key access - len(results) # number of results + print(results["read_a"]) # canonical mapping access + print(results.grep_b) # attribute convenience + list(results) # task names Forces ``return_exceptions=True`` so that failures in one task do not crash the entire batch. Exceptions are converted to diff --git a/cecli/helpers/orchestration/tool_proxy.py b/cecli/helpers/orchestration/tool_proxy.py index 4eb9b098316..1df0d61e554 100644 --- a/cecli/helpers/orchestration/tool_proxy.py +++ b/cecli/helpers/orchestration/tool_proxy.py @@ -9,6 +9,7 @@ import asyncio import json +from copy import deepcopy from typing import Any @@ -63,6 +64,7 @@ def __init__( tool_module: Any = None, mcp_server: Any = None, mcp_tool_name: str = "", + tool_schema: dict[str, Any] | None = None, ) -> None: # Respect the per-coder tool includelist/excludelist filters incl = getattr(coder, "registered_tools", {}).get("included", set()) @@ -78,6 +80,16 @@ def __init__( self._tool_module = tool_module self._mcp_server = mcp_server self._mcp_tool_name = mcp_tool_name + self._tool_schema = ( + tool_schema if tool_schema is not None else getattr(tool_module, "SCHEMA", None) + ) + + def get_schema(self) -> dict[str, Any] | None: + """Return a deep copy of this tool's JSON schema, if available.""" + if not isinstance(self._tool_schema, dict): + return None + + return deepcopy(self._tool_schema) async def __call__(self, *args: Any, **kwargs: Any): """Make the proxy directly callable. @@ -131,12 +143,79 @@ async def __call__(self, *args: Any, **kwargs: Any): return await self.call(**kwargs) + def get_signature(self) -> str | None: + """Return a readable Python-style signature based on the JSON schema. + + Type annotations are best-effort summaries; use the schema for exact + constraints. Optional parameters without defaults display as ``...``. + """ + schema = self._tool_schema + if not isinstance(schema, dict): + return None + + function = schema.get("function", {}) + if not isinstance(function, dict): + return None + + parameters = function.get("parameters", {}) + if not isinstance(parameters, dict): + return None + + properties = parameters.get("properties", {}) + if not isinstance(properties, dict): + return None + + required = parameters.get("required", []) + required = set(required) if isinstance(required, list) else set() + signature_parameters = [] + for name, property_schema in properties.items(): + annotation = self._python_type_name(property_schema) + parameter = f"{name}: {annotation}" + if name not in required: + if isinstance(property_schema, dict) and "default" in property_schema: + parameter += f" = {property_schema['default']!r}" + else: + parameter += " = ..." + signature_parameters.append(parameter) + + function_name = function.get("name") or self._tool_name + if signature_parameters: + return f"{function_name}(*, {', '.join(signature_parameters)})" + return f"{function_name}()" + + @staticmethod + def _python_type_name(schema: Any) -> str: + """Render common JSON Schema types as readable Python type names.""" + if not isinstance(schema, dict): + return "Any" + + schema_type = schema.get("type") + if isinstance(schema_type, list): + type_names = [ToolProxy._python_type_name({"type": item}) for item in schema_type] + return " | ".join(type_names) + + type_names = { + "array": "list", + "boolean": "bool", + "integer": "int", + "number": "float", + "null": "None", + "object": "dict", + "string": "str", + } + if schema_type in type_names: + return type_names[schema_type] + + alternatives = schema.get("anyOf") or schema.get("oneOf") + if isinstance(alternatives, list): + return " | ".join(ToolProxy._python_type_name(item) for item in alternatives) + + return "Any" + def _get_param_names(self) -> list: - """Extract ordered parameter names from the tool's JSON Schema.""" - if self._tool_module is None: - return [] + """Extract parameter names in schema order for positional calls.""" try: - props = self._tool_module.SCHEMA["function"]["parameters"]["properties"] + props = self._tool_schema["function"]["parameters"]["properties"] return list(props.keys()) except (KeyError, TypeError, AttributeError): return [] diff --git a/tests/helpers/test_orchestration.py b/tests/helpers/test_orchestration.py index 583fe20412f..9a278c5211e 100644 --- a/tests/helpers/test_orchestration.py +++ b/tests/helpers/test_orchestration.py @@ -673,7 +673,24 @@ class _MockCoder: mcp_tools = [ ( "MockServer", - [{"type": "function", "function": {"name": "MockTool"}}], + [ + { + "type": "function", + "function": { + "name": "MockTool", + "description": "A mock MCP tool", + "parameters": { + "type": "object", + "properties": { + "param1": {"type": "string"}, + "enabled": {"type": "boolean", "default": False}, + "note": {"type": "string"}, + }, + "required": ["param1"], + }, + }, + } + ], ), ] mcp_manager = _MockMcpManager() @@ -692,6 +709,75 @@ def test_agent_proxy_local_tool_lookup(): assert tool._mcp_server is None, "Local tool should not have _mcp_server" +def test_agent_proxy_get_local_tool_schema_returns_copy(): + """Schema discovery returns a detached JSON schema for local tools.""" + proxy = AgentProxy(_make_mock_coder()) + tool = proxy.get_tool("ReadFile") + + schema = proxy.get_tool_schema("ReadFile") + + assert schema == tool._tool_module.SCHEMA + assert schema is not tool._tool_module.SCHEMA + assert schema["function"] is not tool._tool_module.SCHEMA["function"] + + +def test_agent_proxy_get_mcp_tool_schema_returns_copy(): + """Schema discovery resolves and copies an MCP tool schema.""" + coder = _make_mock_coder_with_mcp() + proxy = AgentProxy(coder) + + schema = proxy.get_tool_schema("MockServer--MockTool") + + assert schema["function"]["name"] == "MockTool" + assert schema is not coder.mcp_tools[0][1][0] + schema["function"]["description"] = "changed" + assert coder.mcp_tools[0][1][0]["function"]["description"] == "A mock MCP tool" + + +def test_agent_proxy_get_tool_schema_raises_for_unknown_tool(): + """Schema discovery preserves get_tool's unknown-name error.""" + proxy = AgentProxy(_make_mock_coder()) + + with pytest.raises(ValueError, match="Unknown tool"): + proxy.get_tool_schema("NonExistentToolXYZ") + + +def test_agent_proxy_mcp_signature_and_positional_call(): + """MCP schemas provide both readable signatures and positional mapping.""" + coder = _make_mock_coder_with_mcp() + proxy = AgentProxy(coder) + + assert proxy.get_tool_signature("MockServer--MockTool") == ( + "MockTool(*, param1: str, enabled: bool = False, note: str = ...)" + ) + + +@pytest.mark.asyncio +async def test_tool_proxy_mcp_positional_dispatch(): + """MCP positional arguments map to schema properties in declaration order.""" + coder = _make_mock_coder_with_mcp() + tool = AgentProxy(coder).get_tool("MockServer--MockTool") + + result = await tool("value1") + + assert "param1" in result["result"][0]["content"] + assert "value1" in result["result"][0]["content"] + + +@pytest.mark.asyncio +async def test_env_agent_get_tool_schema_and_signature(): + """Schema discovery and signature helpers are accessible from sandboxed code.""" + env = _make_env() + + result = await env.execute( + "schema = Agent.get_tool_schema('ReadFile')\n" + "print(schema['function']['name'])\n" + "print(Agent.get_tool_signature('ReadFile'))" + ) + + assert result["results"].startswith("ReadFile\nReadFile(*, ") + + def test_agent_proxy_unknown_tool_raises(): """AgentProxy.get_tool raises ValueError for unknown tool names.""" proxy = AgentProxy(_make_mock_coder()) @@ -1281,7 +1367,7 @@ def test_gather_result_attribute_access(): def test_gather_result_key_access(): - """GatherResult supports key/index access for named results.""" + """GatherResult supports standard string-key lookup.""" from cecli.helpers.orchestration.environment import GatherResult gr = GatherResult({"x": 1, "y": 2}) @@ -1307,14 +1393,24 @@ def test_gather_result_contains(): def test_gather_result_iteration(): - """GatherResult is iterable (yields values).""" + """GatherResult iteration follows Mapping semantics and yields keys.""" + from cecli.helpers.orchestration.environment import GatherResult + + gr = GatherResult({"a": 10, "b": 20}) + assert list(gr) == ["a", "b"] + assert dict(gr) == {"a": 10, "b": 20} + + +def test_gather_result_mapping_views(): + """GatherResult exposes standard mapping views and lookup helpers.""" from cecli.helpers.orchestration.environment import GatherResult gr = GatherResult({"a": 10, "b": 20}) - values = list(gr) - assert ("a", 10) in values - assert ("b", 20) in values - assert len(values) == 2 + assert list(gr.keys()) == ["a", "b"] + assert list(gr.values()) == [10, 20] + assert list(gr.items()) == [("a", 10), ("b", 20)] + assert gr.get("a") == 10 + assert gr.get("missing", 0) == 0 def test_gather_result_read_only(): From 5849d9857176e71ef4d5bdb2ed31f3311383b9d5 Mon Sep 17 00:00:00 2001 From: Dustin Washington Date: Wed, 23 Sep 2026 00:04:18 -0400 Subject: [PATCH 10/10] Fix formatting --- cecli/mcp/server.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/cecli/mcp/server.py b/cecli/mcp/server.py index bb3cf4fc279..fea2c475eb6 100644 --- a/cecli/mcp/server.py +++ b/cecli/mcp/server.py @@ -337,9 +337,7 @@ async def _enter_client_session(self, read, write): ClientSession( read, write, - read_timeout_seconds=_client_session_read_timeout( - self._request_timeout_seconds() - ), + read_timeout_seconds=_client_session_read_timeout(self._request_timeout_seconds()), ) ) await session.initialize()