feat(aws-bedrock/us.openai.gpt-5.6-sol): add new models [bot] - #2204
Merged
Archit-Kumar-16 merged 4 commits intoAug 24, 2026
Merged
Conversation
Contributor
|
/test-models |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
… reasoning_effort values, add function_calling and output limits
Contributor
|
/test-models |
…S model card and fix limits The entry carried OpenAI direct-API list prices ($5.00 in / $30.00 out per 1M) instead of the Amazon Bedrock rates. Input was 25% high and output 50% high on both the base rate and the >272K long-context tier, with the cache read/write rates off by the same factors. Corrected to the Geo CRIS table on the model card, per 1M tokens: <=272K in $4.40 cache write $5.50 cache read $0.44 out $22.00 >272K in $8.80 cache write $11.00 cache read $0.88 out $33.00 Also sets the context limits OpenAI publishes for the gpt-5.6 tiers (1,050,000 window = 922,000 max input + 128,000 max output; the AWS card states the same window rounded to "1M"), and aligns the feature list with Terra and Luna, whose AWS model cards are identical to Sol's. structured_output stays off: the card lists Structured outputs as not supported on the bedrock-runtime endpoint. Sources: https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html https://developers.openai.com/api/docs/models/gpt-5.6-sol
Contributor
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit a2d196f. Configure here.
Archit-Kumar-16
approved these changes
Aug 24, 2026
Archit-Kumar-16
deleted the
bot/add-aws-bedrock-us.openai.gpt-5.6-sol-20260820-091709
branch
August 24, 2026 04:39
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Auto-generated by model-addition-agent for
aws-bedrock/us.openai.gpt-5.6-sol.Note
Low Risk
Data-only model catalog YAML with no runtime, auth, or billing-code changes. Risk is limited to incorrect pricing or capability metadata.
Overview
Adds Bedrock catalog metadata for
us.openai.gpt-5.6-solso the model can be used as a serverless chat/responses model with thinking enabled.The entry includes US-region pricing (with cumulative tiers above 272k tokens and prompt-cache rates), a ~1.05M context window, text/image input, tools/JSON/caching features, and a
reasoning_effortparam defaulting tomedium.Reviewed by Cursor Bugbot for commit a2d196f. Bugbot is set up for automated code reviews on this repo. Configure here.