Skip to content

chore: update model catalog from bot issues - #1173

Merged
Erin McNulty (erin2722) merged 1 commit into
mainfrom
chore/autofix-bot-issues-2026-08-27
Aug 27, 2026
Merged

chore: update model catalog from bot issues#1173
Erin McNulty (erin2722) merged 1 commit into
mainfrom
chore/autofix-bot-issues-2026-08-27

Conversation

@github-actions

Copy link
Copy Markdown
Contributor

Automated daily batch of model catalog updates from bot issues.

Included issues

Summary

Issue Provider Primary model Changed models Added models Updated models Verification sources
#1161 mistral magistral-medium-latest magistral-medium-latest
magistral-small-latest
None magistral-medium-latest
magistral-small-latest
1
2
3
#1165 mistral mistral-large-latest mistral-large-latest
mistral-medium-3.5
mistral-small-latest
None mistral-large-latest
mistral-medium-3.5
mistral-small-latest
1
2
#1170 together zai-org/GLM-5.3-Flash zai-org/GLM-5.3-Flash None zai-org/GLM-5.3-Flash 1
#1171 databricks databricks-grok-4-6 databricks-grok-4-6 databricks-grok-4-6 None 1
2

Verified metadata

#1161: [BOT ISSUE] Mistral: magistral-medium-latest and magistral-small-latest missing deprecation markers

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
magistral-medium-latest Magistral Medium Latest mistral openai chat input=128000, output=40000 in/out=2/5 per 1M deprecated=true; date=2026-07-31
magistral-small-latest Magistral Small Latest mistral openai chat input=128000, output=40000 in/out=0.5/1.5 per 1M deprecated=true; date=2026-07-31

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
magistral-medium-latest max_input_tokens 128000 40000 mistral/magistral-medium-latest
magistral-medium-latest deprecation_date 2026-07-31 n/a mistral/magistral-medium-latest
magistral-small-latest max_input_tokens 128000 40000 mistral/magistral-small-latest
magistral-small-latest deprecation_date 2026-07-31 n/a mistral/magistral-small-latest

#1165: [BOT ISSUE] Mistral: add missing cached input pricing for flagship models

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
mistral-large-latest Mistral Large mistral openai chat input=262144, output=262144 in/out=0.5/1.5 per 1M; cache read=0.05 per 1M multimodal=true
mistral-medium-3.5 Mistral Medium 3.5 mistral openai chat input=256000, output=not provided in/out=1.5/7.5 per 1M; cache read=0.15 per 1M multimodal=true; reasoning=true
mistral-small-latest Mistral Small mistral openai chat input=262144, output=131072 in/out=0.15/0.6 per 1M; cache read=0.015 per 1M 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
mistral-large-latest input_cache_read_cost_per_mil_tokens 0.05 n/a mistral/mistral-large-latest
mistral-medium-3.5 catalog entry present missing None
mistral-small-latest max_output_tokens 131072 262144 mistral/mistral-small-latest
mistral-small-latest input_cache_read_cost_per_mil_tokens 0.015 n/a mistral/mistral-small-latest

#1170: [BOT ISSUE] Together: add together provider to zai-org/GLM-5.3-Flash

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
zai-org/GLM-5.3-Flash GLM 5.3 Flash baseten, together openai chat input=1048576, output=131072 in/out=0.15/0.5 per 1M; cache read=0.03 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
zai-org/GLM-5.3-Flash catalog entry present missing None

#1171: [BOT ISSUE] Databricks: add missing databricks-grok-4-6

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
databricks-grok-4-6 Grok 4.6 databricks openai chat input=500000, output=not provided n/a 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
databricks-grok-4-6 catalog entry present missing None

@vercel

vercel Bot commented Aug 27, 2026

Copy link
Copy Markdown

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

Project Deployment Actions Updated (UTC)
ai-proxy Ready Ready Preview Aug 27, 2026 1:42pm

Request Review

@github-actions

Copy link
Copy Markdown
Contributor Author

Codex (@codex) review

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 75f068fd76

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".

"zai-org/GLM-5.2": ["baseten", "together"],
"zai-org/GLM-5.2-Fast": ["baseten"],
"zai-org/GLM-5.3-Flash": ["baseten"],
"zai-org/GLM-5.3-Flash": ["baseten", "together"],

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P1 Badge Move endpoint mappings to gateway

This change updates AvailableEndpointTypes in the deprecated proxy; the same issue also applies to the new Databricks mapping later in this object. Provider-routing changes belong in the parent ../gateway/ implementation, while only the model_list.json catalog updates should remain in this repository.

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

Useful? React with 👍 / 👎.

@erin2722
Erin McNulty (erin2722) merged commit 88388ac into main Aug 27, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

1 participant