chore: update model catalog from bot issues

[github-actions]

Automated daily batch of model catalog updates from bot issues.

Included issues

• Closes [BOT ISSUE] Bedrock: fix incorrect pricing for openai.gpt-5.6-terra and openai.gpt-5.6-luna #1061: [BOT ISSUE] Bedrock: fix incorrect pricing for openai.gpt-5.6-terra and openai.gpt-5.6-luna

Summary

Issue	Provider	Primary model	Changed models	Added models	Updated models	Verification sources
#1061	bedrock	openai.gpt-5.6-terra	openai.gpt-5.6-terra openai.gpt-5.6-luna	None	openai.gpt-5.6-terra openai.gpt-5.6-luna	1 2 3

Verified metadata

#1061: [BOT ISSUE] Bedrock: fix incorrect pricing for openai.gpt-5.6-terra and openai.gpt-5.6-luna

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
openai.gpt-5.6-terra	OpenAI GPT-5.6 Terra (Bedrock)		bedrock	openai	chat	input=272000, output=not provided	in/out=2.2/13.2 per 1M; cache read=0.22 per 1M; cache write=2.75 per 1M	multimodal=true; reasoning=true
openai.gpt-5.6-luna	OpenAI GPT-5.6 Luna (Bedrock)		bedrock	openai	chat	input=272000, output=not provided	in/out=0.22/1.32 per 1M; cache read=0.022 per 1M; cache write=0.275 per 1M	multimodal=true; reasoning=true

Verification notes

Verification

sync_models vs proposed update

sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.

Model	Field	Proposed update	sync_models	sync_models source models
openai.gpt-5.6-terra	catalog entry	present	missing	None
openai.gpt-5.6-luna	catalog entry	present	missing	None

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview	Aug 5, 2026 11:05am

[github-actions]

Codex (@codex) review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: fe784f1625

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "Codex (@codex) review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".

[chatgpt-codex-connector]

Use Bedrock's in-region GPT-5.6 prices

For this Bedrock model ID (and the Luna block just below), these are the discounted/global-looking rates, but AWS documents openai.gpt-5.6-terra/openai.gpt-5.6-luna as bedrock-mantle in-region model IDs with no Geo or Global inference IDs, and the Amazon Bedrock pricing page still lists the in-region rates as Terra $2.75/$3.44/$0.28/$16.50 and Luna $1.10/$1.38/$0.11/$6.60. With the lower values here, any catalog-based Bedrock cost estimate for these IDs underreports actual in-region usage. Sources: https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html and https://aws.amazon.com/bedrock/pricing/

Useful? React with 👍 / 👎.