Skip to content

DUX-11651: Update Bedrock pricing for gpt-5.6-luna/terra July 2026 price cut #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
samuelboland merged 1 commit into from
Aug 7, 2026
Merged

DUX-11651: Update Bedrock pricing for gpt-5.6-luna/terra July 2026 price cut #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 16 additions & 16 deletions lib/ruby_llm/models.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16812,10 +16812,10 @@
"pricing": {
"text_tokens": {
"standard": {
"input_per_million": 1.0,
"output_per_million": 6.0,
"cache_read_input_per_million": 0.1,
"cache_write_input_per_million": 1.25
"input_per_million": 0.22,
"output_per_million": 1.32,
"cache_read_input_per_million": 0.022,
"cache_write_input_per_million": 0.275
}
}
},
Expand All @@ -16840,10 +16840,10 @@
}
],
"cost": {
"input": 1.0,
"output": 6.0,
"cache_read": 0.1,
"cache_write": 1.25
"input": 0.22,
"output": 1.32,
"cache_read": 0.022,
"cache_write": 0.275
},
"limit": {
"context": 272000,
Expand Down Expand Up @@ -16948,10 +16948,10 @@
"pricing": {
"text_tokens": {
"standard": {
"input_per_million": 2.5,
"output_per_million": 15.0,
"cache_read_input_per_million": 0.25,
"cache_write_input_per_million": 3.125
"input_per_million": 2.2,
"output_per_million": 13.2,
"cache_read_input_per_million": 0.22,
"cache_write_input_per_million": 2.75
Comment on lines +16951 to +16954

@staging-supernova-dx-appf-io staging-supernova-dx-appf-io Bot Aug 7, 2026

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The new Terra pricing doesn't match the stated price cut. This PR's description says Terra was $10.00/$60.00 (input/output) and is being cut to $2.20/$13.20 — the same 0.22x ratio applied to Luna. But the pre-PR value in this file was actually input: 2.5, output: 15.0 (visible on main), not 10/60. So the diff only reduces Terra's price by ~12% (2.5→2.2), while Luna gets the full ~78% cut (1.0→0.22) described as the same pricing event. Either the PR description is based on stale/wrong "before" figures, or Terra's new rate should be 2.5 * 0.22 ≈ 0.55 (output 3.3) to match the same proportional cut Luna received — please double-check against the actual AWS Bedrock pricing page before merging.

}
}
},
Expand All @@ -16976,10 +16976,10 @@
}
],
"cost": {
"input": 2.5,
"output": 15.0,
"cache_read": 0.25,
"cache_write": 3.125
"input": 2.2,
"output": 13.2,
"cache_read": 0.22,
"cache_write": 2.75
},
"limit": {
"context": 272000,
Expand Down
10 changes: 8 additions & 2 deletions spec/ruby_llm/models_gpt_5_6_bedrock_spec.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,12 @@
# registry carrying a cache_write_input_per_million value — every other
# OpenAI entry has none because the rate really is $0 for those models.
#
# Luna/Terra base input/output rates reflect the July 30, 2026 OpenAI/Bedrock
# price cut (AWS Bedrock pricing page: aws.amazon.com/bedrock/pricing; OpenAI's
# July 30, 2026 pricing announcement). cache_read (0.1x) and cache_write (1.25x)
# remain the same ratios of the (now lower) input rate as before. Sol was not
# part of this price cut and is unchanged.
#
# Separately open (do NOT resolve here): OpenAI's developer community has
# reported two GPT-5.6-specific usage-accounting bugs since launch (July
# 2026) — one where cached_tokens + cache_write_tokens could nearly
Expand All @@ -27,8 +33,8 @@
# Luna/Terra/Sol costs as an open risk until this is checked.
{
'openai.gpt-5.6-sol' => { input: 5.0, output: 30.0, cache_read: 0.5, cache_write: 6.25 },
'openai.gpt-5.6-terra' => { input: 2.5, output: 15.0, cache_read: 0.25, cache_write: 3.125 },
'openai.gpt-5.6-luna' => { input: 1.0, output: 6.0, cache_read: 0.1, cache_write: 1.25 }
'openai.gpt-5.6-terra' => { input: 2.2, output: 13.2, cache_read: 0.22, cache_write: 2.75 },
'openai.gpt-5.6-luna' => { input: 0.22, output: 1.32, cache_read: 0.022, cache_write: 0.275 }
}.each do |id, cost|
it "resolves #{id} from the bedrock provider with the documented effort values" do
model = RubyLLM.models.find(id, :bedrock)
Expand Down