Skip to content

fix: update xAI model metadata for grok-4-1-fast-reasoning +7 more#710

Merged
Erin McNulty (erin2722) merged 3 commits into
mainfrom
chore/autofix-issue-700
Jun 1, 2026
Merged

fix: update xAI model metadata for grok-4-1-fast-reasoning +7 more#710
Erin McNulty (erin2722) merged 3 commits into
mainfrom
chore/autofix-issue-700

Conversation

@github-actions
Copy link
Copy Markdown
Contributor

@github-actions github-actions Bot commented Jun 1, 2026

fix: update xAI model metadata for grok-4-1-fast-reasoning +7 more

Closes #700

Source issue: #700

Summary

Field Value
Provider xai
Primary model grok-4-1-fast-reasoning
Changed models grok-4-1-fast-reasoning
grok-4-1-fast-non-reasoning
grok-4-fast-reasoning
grok-4-fast-non-reasoning
grok-4-1-fast-reasoning-latest
grok-4-1-fast-non-reasoning-latest
grok-4-fast-reasoning-latest
grok-4-fast-non-reasoning-latest
Added models None
Updated models grok-4-1-fast-reasoning
grok-4-1-fast-non-reasoning
grok-4-fast-reasoning
grok-4-fast-non-reasoning
grok-4-1-fast-reasoning-latest
grok-4-1-fast-non-reasoning-latest
grok-4-fast-reasoning-latest
grok-4-fast-non-reasoning-latest
Verification sources 1
2

Verified metadata

Model Display name Parent Providers Format Flavor Token limits Pricing Lifecycle
grok-4-1-fast-reasoning grok-4-1-fast-reasoning-latest xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M parent=grok-4-1-fast-reasoning-latest; deprecated=true; date=2026-05-15; multimodal=true
grok-4-1-fast-non-reasoning grok-4-1-fast-non-reasoning-latest xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M parent=grok-4-1-fast-non-reasoning-latest; deprecated=true; date=2026-05-15; multimodal=true
grok-4-fast-reasoning grok-4-fast-reasoning-latest xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M parent=grok-4-fast-reasoning-latest; deprecated=true; date=2026-05-15; multimodal=true
grok-4-fast-non-reasoning grok-4-fast-non-reasoning-latest xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M parent=grok-4-fast-non-reasoning-latest; deprecated=true; date=2026-05-15; multimodal=true
grok-4-1-fast-reasoning-latest Grok 4.1 Fast xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M deprecated=true; date=2026-05-15; multimodal=true
grok-4-1-fast-non-reasoning-latest Grok 4.1 Fast (Non-Reasoning) xAI openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M deprecated=true; date=2026-05-15; multimodal=true
grok-4-fast-reasoning-latest Grok 4 Fast n/a openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M deprecated=true; date=2026-05-15; multimodal=true
grok-4-fast-non-reasoning-latest Grok 4 Fast (Non-Reasoning) n/a openai chat input=2000000, output=2000000 in/out=0.2/0.5 per 1M; cache read=0.05 per 1M deprecated=true; date=2026-05-15; multimodal=true

Verification notes

Verification

  • Source 1: xAI May 15, 2026 Model Retirement page — confirms grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning, grok-4-fast-reasoning, and grok-4-fast-non-reasoning were retired on 2026-05-15 with replacement grok-4.3. This source verified deprecated and deprecation_date for these four model IDs.
  • Source 2: xAI models page — none of the 8 model IDs (including -latest aliases) appear on the active models listing. This confirms the -latest aliases are also retired since they pointed to the now-retired base models.
  • sync_models (LiteLLM): None of the 8 model IDs appear in the LiteLLM model_prices_and_context_window_backup.json catalog, so no cross-check comparison is applicable. No numeric fields are being changed — only deprecated and deprecation_date are added.
  • Fields not changed: No numeric fields (token limits, pricing) are modified. Only deprecated: true and deprecation_date: "2026-05-15" are added to each existing entry.
  • All 8 models verified: The 4 base model IDs are explicitly listed on the retirement page. The 4 -latest aliases are confirmed absent from the active models page, consistent with the base models' retirement.

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
grok-4-1-fast-reasoning deprecation_date 2026-05-15 n/a xai/grok-4-1-fast-reasoning
grok-4-1-fast-non-reasoning deprecation_date 2026-05-15 n/a xai/grok-4-1-fast-non-reasoning
grok-4-fast-reasoning deprecation_date 2026-05-15 n/a xai/grok-4-fast-reasoning
grok-4-fast-non-reasoning deprecation_date 2026-05-15 n/a xai/grok-4-fast-non-reasoning
grok-4-1-fast-reasoning-latest deprecation_date 2026-05-15 n/a xai/grok-4-1-fast-reasoning-latest
grok-4-1-fast-non-reasoning-latest deprecation_date 2026-05-15 n/a xai/grok-4-1-fast-non-reasoning-latest
grok-4-fast-reasoning-latest catalog entry present missing None
grok-4-fast-non-reasoning-latest catalog entry present missing None

@vercel
Copy link
Copy Markdown

vercel Bot commented Jun 1, 2026

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

Project Deployment Actions Updated (UTC)
ai-proxy Ready Ready Preview, Comment Jun 1, 2026 10:15pm

Request Review

Copy link
Copy Markdown

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

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: f339e5ea35

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".

Comment on lines +6839 to +6840
"deprecated": true,
"deprecation_date": "2026-05-15",
Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Update redirected xAI slugs to Grok 4.3 pricing

When these slugs are marked retired as of 2026-05-15, their pricing needs to change as well: xAI's retirement notice says requests to the retired slugs continue to resolve by redirecting to grok-4.3 and are billed at Grok 4.3 rates ($1.25 input / $2.50 output per 1M), while this entry still advertises the old $0.20 / $0.50 rates. Any existing traffic or historical cost calculation keyed by these deprecated model IDs will therefore be undercounted after the deprecation date; the same mismatch applies to the other Grok fast entries updated in this patch.

Useful? React with 👍 / 👎.

@erin2722 Erin McNulty (erin2722) merged commit 4a7af50 into main Jun 1, 2026
5 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BOT ISSUE] xAI: mark retired grok-4-fast and grok-4-1-fast models as deprecated

2 participants