chore: update model catalog from bot issues

[github-actions]

Automated daily batch of model catalog updates from bot issues.

Included issues

• Closes [BOT ISSUE] Databricks: add missing databricks-gemini-3-6-flash, databricks-glm-5-2, and databricks-inkling #1011: [BOT ISSUE] Databricks: add missing databricks-gemini-3-6-flash, databricks-glm-5-2, and databricks-inkling
• Closes [BOT ISSUE] Bedrock: add missing google.gemma-3-12b-it, google.gemma-3-4b-it, and nvidia.nemotron-nano-9b-v2 #1012: [BOT ISSUE] Bedrock: add missing google.gemma-3-12b-it, google.gemma-3-4b-it, and nvidia.nemotron-nano-9b-v2
• Closes [BOT ISSUE] Add missing Bedrock entries for OpenAI GPT-5.6 (Sol, Terra, Luna) #1013: [BOT ISSUE] Add missing Bedrock entries for OpenAI GPT-5.6 (Sol, Terra, Luna)
• Closes [BOT ISSUE] Mistral: add deprecation markers for retired mistral-small-2501, mistral-saba-2502, and mistral-saba-latest #1015: [BOT ISSUE] Mistral: add deprecation markers for retired mistral-small-2501, mistral-saba-2502, and mistral-saba-latest

Summary

Issue	Provider	Primary model	Changed models	Added models	Updated models	Verification sources
#1011	databricks	databricks-gemini-3-6-flash	databricks-gemini-3-6-flash databricks-glm-5-2 databricks-inkling	databricks-gemini-3-6-flash databricks-glm-5-2 databricks-inkling	None	1 2
#1012	bedrock	google.gemma-3-12b-it	google.gemma-3-12b-it google.gemma-3-4b-it nvidia.nemotron-nano-9b-v2	google.gemma-3-12b-it google.gemma-3-4b-it nvidia.nemotron-nano-9b-v2	None	1 2 3 4
#1013	bedrock	openai.gpt-5.6-sol	openai.gpt-5.6-sol openai.gpt-5.6-terra openai.gpt-5.6-luna	openai.gpt-5.6-sol openai.gpt-5.6-terra openai.gpt-5.6-luna	None	1 2 3 4 5
#1015	mistral	mistral-small-2501	mistral-small-2501 mistral-saba-2502 mistral-saba-latest	None	mistral-small-2501 mistral-saba-2502 mistral-saba-latest	1

Verified metadata

#1011: [BOT ISSUE] Databricks: add missing databricks-gemini-3-6-flash, databricks-glm-5-2, and databricks-inkling

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
databricks-gemini-3-6-flash	Gemini 3.6 Flash		databricks	openai	chat	input=1048576, output=65536	n/a	multimodal=true; reasoning=true
databricks-glm-5-2	GLM 5.2		databricks	openai	chat	input=262144, output=128000	n/a	reasoning=true
databricks-inkling	Inkling		databricks	openai	chat	input=1048576, output=not provided	n/a	multimodal=true; reasoning=true

Verification notes

No LLM verification step ran; model metadata was already complete in the issue.

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
databricks-gemini-3-6-flash	catalog entry	present	missing	None
databricks-glm-5-2	catalog entry	present	missing	None
databricks-inkling	catalog entry	present	missing	None

#1012: [BOT ISSUE] Bedrock: add missing google.gemma-3-12b-it, google.gemma-3-4b-it, and nvidia.nemotron-nano-9b-v2

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
google.gemma-3-12b-it	Gemma 3 12B IT		bedrock	openai	chat	input=128000, output=8000	in/out=0.09/0.29 per 1M	multimodal=true
google.gemma-3-4b-it	Gemma 3 4B IT		bedrock	openai	chat	input=128000, output=8000	in/out=0.04/0.08 per 1M	multimodal=true
nvidia.nemotron-nano-9b-v2	NVIDIA Nemotron Nano 9B v2		bedrock	converse	chat	input=128000, output=8000	in/out=0.06/0.23 per 1M	active

Verification notes

No LLM verification step ran; model metadata was already complete in the issue.

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
google.gemma-3-12b-it	max_output_tokens	8000	8192	google.gemma-3-12b-it
google.gemma-3-4b-it	max_output_tokens	8000	8192	google.gemma-3-4b-it
nvidia.nemotron-nano-9b-v2	max_output_tokens	8000	8192	nvidia.nemotron-nano-9b-v2

#1013: [BOT ISSUE] Add missing Bedrock entries for OpenAI GPT-5.6 (Sol, Terra, Luna)

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
openai.gpt-5.6-sol	OpenAI GPT-5.6 Sol (Bedrock)		bedrock	openai	chat	input=272000, output=not provided	in/out=5.5/33 per 1M; cache read=0.55 per 1M	multimodal=true; reasoning=true
openai.gpt-5.6-terra	OpenAI GPT-5.6 Terra (Bedrock)		bedrock	openai	chat	input=272000, output=not provided	in/out=2.75/16.5 per 1M; cache read=0.28 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=1.1/6.6 per 1M; cache read=0.11 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-sol	catalog entry	present	missing	None
openai.gpt-5.6-terra	catalog entry	present	missing	None
openai.gpt-5.6-luna	catalog entry	present	missing	None

#1015: [BOT ISSUE] Mistral: add deprecation markers for retired mistral-small-2501, mistral-saba-2502, and mistral-saba-latest

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
mistral-small-2501		mistral-small-latest	mistral	openai	chat	input=n/a, output=not provided	in/out=0.1/0.3 per 1M	parent=mistral-small-latest; date=2025-11-30
mistral-saba-2502		mistral-saba-latest	mistral	openai	chat	input=n/a, output=not provided	in/out=0.2/0.6 per 1M	parent=mistral-saba-latest; date=2025-09-30
mistral-saba-latest	Mistral Saba		mistral	openai	chat	input=n/a, output=not provided	in/out=0.2/0.6 per 1M	date=2025-09-30

Verification notes

No LLM verification step ran; model metadata was already complete in the issue.

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
mistral-small-2501	catalog entry	present	missing	None
mistral-saba-2502	catalog entry	present	missing	None
mistral-saba-latest	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, Comment	Jul 24, 2026 10:52am

[github-actions]

Codex (@codex) review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 1ee7554ed7

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]

Move endpoint routing changes to gateway

Adding entries to AvailableEndpointTypes changes model-to-provider routing in this deprecated proxy package; the repository guidance says routing fixes belong in ../gateway/, with model_list.json as the valid exception here. Keeping these mappings here makes the deprecated proxy diverge while the active gateway will not receive the routing update.

AGENTS.md reference: AGENTS.md:L6-L15

Useful? React with 👍 / 👎.