Skip to content

chore: update model catalog from bot issues - #848

Merged
Erin McNulty (erin2722) merged 4 commits into
mainfrom
chore/autofix-bot-issues-2026-06-23
Jun 23, 2026
Merged

chore: update model catalog from bot issues#848
Erin McNulty (erin2722) merged 4 commits into
mainfrom
chore/autofix-bot-issues-2026-06-23

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
#835 openai chat-latest chat-latest None chat-latest 1
#837 openai gpt-5.5-pro gpt-5.5-pro
gpt-5.5-pro-2026-04-23
gpt-5.4-pro
gpt-5.4-pro-2026-03-05
None gpt-5.5-pro
gpt-5.5-pro-2026-04-23
gpt-5.4-pro
gpt-5.4-pro-2026-03-05
1
2
#838 openai gpt-4o-2024-05-13 gpt-4o-2024-05-13
o1-2024-12-17
o4-mini-2025-04-16
None gpt-4o-2024-05-13
o1-2024-12-17
o4-mini-2025-04-16
1
#839 openai gpt-5-2025-08-07 gpt-5-2025-08-07
o3-2025-04-16
gpt-5-mini-2025-08-07
None gpt-5-2025-08-07
o3-2025-04-16
gpt-5-mini-2025-08-07
1
#841 cerebras gpt-oss-120b gpt-oss-120b None gpt-oss-120b 1
2
3
#842 perplexity r1-1776 r1-1776 None r1-1776 1
2

Verified metadata

#835: [BOT ISSUE] OpenAI: add missing pricing for chat-latest

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
chat-latest GPT Chat Latest openai, azure openai chat input=128000, output=16384 in/out=5/30 per 1M; cache read=0.5 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
chat-latest catalog entry present missing None

#837: [BOT ISSUE] OpenAI: remove incorrect cached input pricing from gpt-5.5-pro and gpt-5.4-pro

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
gpt-5.5-pro GPT-5.5 Pro openai, azure openai chat input=1050000, output=128000 in/out=30/180 per 1M; cache read=null per 1M multimodal=true; reasoning=true
gpt-5.5-pro-2026-04-23 GPT-5.5 Pro (2026-04-23) gpt-5.5-pro openai, azure openai chat input=1050000, output=128000 in/out=30/180 per 1M; cache read=null per 1M parent=gpt-5.5-pro; multimodal=true; reasoning=true
gpt-5.4-pro GPT-5.4 Pro openai, azure openai chat input=1050000, output=128000 in/out=30/180 per 1M; cache read=null per 1M multimodal=true; reasoning=true
gpt-5.4-pro-2026-03-05 GPT-5.4 Pro (2026-03-05) gpt-5.4-pro openai, azure openai chat input=1050000, output=128000 in/out=30/180 per 1M; cache read=null per 1M parent=gpt-5.4-pro; 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
gpt-5.5-pro input_cache_read_cost_per_mil_tokens n/a 3 gpt-5.5-pro
gpt-5.5-pro-2026-04-23 input_cache_read_cost_per_mil_tokens n/a 3 gpt-5.5-pro-2026-04-23
gpt-5.4-pro input_cache_read_cost_per_mil_tokens n/a 3 gpt-5.4-pro
gpt-5.4-pro-2026-03-05 input_cache_read_cost_per_mil_tokens n/a 3 gpt-5.4-pro-2026-03-05

#838: [BOT ISSUE] OpenAI: add deprecation_date for gpt-4o-2024-05-13, o1-2024-12-17, o4-mini-2025-04-16

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
gpt-4o-2024-05-13 GPT-4o (2024-05-13) gpt-4o openai, azure openai chat input=128000, output=4096 in/out=5/15 per 1M parent=gpt-4o; date=2026-10-23; multimodal=true
o1-2024-12-17 o1 (2024-12-17) o1 openai, azure openai chat input=200000, output=100000 in/out=15/60 per 1M; cache read=7.5 per 1M parent=o1; date=2026-10-23; multimodal=true; reasoning=true
o4-mini-2025-04-16 o4-mini (2025-04-16) o4-mini openai, azure openai chat input=200000, output=100000 in/out=1.1/4.4 per 1M; cache read=0.275 per 1M parent=o4-mini; date=2026-10-23; 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
gpt-4o-2024-05-13 deprecation_date 2026-10-23 n/a gpt-4o-2024-05-13
o1-2024-12-17 deprecation_date 2026-10-23 n/a o1-2024-12-17
o4-mini-2025-04-16 deprecation_date 2026-10-23 n/a o4-mini-2025-04-16

#839: [BOT ISSUE] OpenAI: add deprecation_date for gpt-5-2025-08-07, o3-2025-04-16, gpt-5-mini-2025-08-07

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
gpt-5-2025-08-07 GPT-5 (2025-08-07) gpt-5 openai, azure openai chat input=272000, output=128000 in/out=1.25/10 per 1M; cache read=0.125 per 1M parent=gpt-5; date=2026-12-11; multimodal=true; reasoning=true
o3-2025-04-16 o3 (2025-04-16) o3 openai, azure openai chat input=200000, output=100000 in/out=2/8 per 1M; cache read=0.5 per 1M parent=o3; date=2026-12-11; multimodal=true; reasoning=true
gpt-5-mini-2025-08-07 GPT-5 mini (2025-08-07) gpt-5-mini openai, azure openai chat input=272000, output=128000 in/out=0.25/2 per 1M; cache read=0.025 per 1M parent=gpt-5-mini; date=2026-12-11; 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
gpt-5-2025-08-07 deprecation_date 2026-12-11 n/a gpt-5-2025-08-07
o3-2025-04-16 deprecation_date 2026-12-11 n/a o3-2025-04-16
gpt-5-mini-2025-08-07 deprecation_date 2026-12-11 n/a gpt-5-mini-2025-08-07

#841: [BOT ISSUE] Cerebras: update gpt-oss-120b max_output_tokens from 32768 to 40960

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
gpt-oss-120b OpenAI GPT-OSS (120B) cerebras openai chat input=131072, output=40960 in/out=0.35/0.75 per 1M 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
gpt-oss-120b max_output_tokens 40960 32768 cerebras/gpt-oss-120b

#842: [BOT ISSUE] Perplexity: mark r1-1776 as deprecated (retired August 2025)

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
r1-1776 R1 1776 n/a openai chat input=n/a, output=not provided in/out=2/8 per 1M deprecated=true; date=2025-08-01

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
r1-1776 catalog entry present missing None

@vercel

vercel Bot commented Jun 23, 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, Comment Jun 23, 2026 7:10pm

Request Review

@github-actions

Copy link
Copy Markdown
Contributor Author

Codex (@codex) review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. What shall we delve into next?

Reviewed commit: e58dd66f49

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".

@github-actions

Copy link
Copy Markdown
Contributor Author

Codex Review Response

Codex found no issues with the automated model catalog update (PR #848). No repository changes were made.

Erin McNulty (erin2722) and others added 2 commits June 23, 2026 17:22
Merged current main (which has #849 Baseten pricing + #845 baseten provider
source + the deprecated-model exclusions). The 3-way merge dropped all of this
batch's regressions (they reverted values main now owns) and kept only the
net-new metadata: chat-latest pricing, r1-1776 deprecation, the OpenAI dated-
snapshot deprecation dates, the gpt-5.x-pro input_cache_read cleanup, and the
groq gpt-oss-120b max_output bump. This commit fixes the ["openai","azure"]
comma-spacing prettier violation the bot reintroduced in index.ts.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Every bot catalog PR has been reintroducing AvailableEndpointTypes entries like
["openai","azure"] (no space after the comma), which fails the prettier
pre-commit hook. Two fixes so the scripts never output unlinted code:

1. fix_bot_issue.ts wrote entries with JSON.stringify(providers), which omits
   the space prettier requires. Format the array as
   ["openai", "azure"] instead.
2. normalize-local-models (the last write step in both the sync-models and
   fix-missing-model-bot-issues workflows, run after the LLM enrichment and
   Codex-response edits) now runs Prettier on schema/index.ts before finishing.
   This is the catch-all: it formats whatever those LLM steps or any other
   writer produced, guaranteeing a lint-clean index.ts at commit time.
   model_list.json is intentionally excluded from the prettier hook, so it is
   canonicalized separately and not run through Prettier.

Verified: injecting a no-space entry and running normalize-local-models --write
reformats it to the spaced style and prettier --check then passes. prettier is
already a root devDependency (3.3.2). No new tsc errors (5 pre-existing in each
file unchanged); 28 vitest tests pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@erin2722
Erin McNulty (erin2722) merged commit 10541ba into main Jun 23, 2026
5 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment