Skip to content
Model Change Index
  • OverviewNext shutdowns and latest changes
  • ShutdownsEvery date, one row per platform
  • ChangesReleases, deprecations, redirects and prices
  • LeaderboardEvery model, its scores and price
  • Check my stackYour models on one timeline
Track my stack

Grok 4.1 Fast (Reasoning)

ActivexAIxai/grok-4-1-fast-reasoning3 platforms

Redirected. Grok 4.1 Fast (Reasoning) is active on 3 platforms, with no shutdown date announced. xAI names Grok 4.3 as the replacement.

Next shutdown
None setNo date on 3 platforms
Arena Text
1,430#57 of 128 · Arena
Arena WebDev
1,242#63 of 69 · Arena
Context window
2Mtokens
Released
Nov 19, 2025xAI

Dates on every platform

3 listings · a floor is the earliest possible date
Grok 4.1 Fast (Reasoning) on each platform: model ID, status, dates, replacement and source
PlatformModel ID and statusDeprecatedShuts downReplacement
Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026grok-4-1-fast-reasoning:1Active–None set–
Google Vertex AIGoogle Cloud: Gemini Enterprise Agent Platform release notes (opens in a new tab) · checked Oct 14, 2026grok-4.1-fast-reasoningShut down · also xai/grok-4.1-fast-reasoning–
xAI APIxAI: Grok Model Retirement on May 15, 2026 (opens in a new tab) · checked Oct 14, 2026grok-4-1-fast-reasoningShut down–Grok 4.3

Since the retirement, requests to grok-4-1-fast-reasoning are served by grok-4.3 with low reasoning effort and billed at grok-4.3 rates.

Since May 15, 2026, requests to grok-4-1-fast-reasoning on xAI API are answered by Grok 4.3, with no error. Behavior and price follow the newer model.

What breaks when you move off Grok 4.1 Fast (Reasoning)

  • Pricing

    Requests to the retired slugs are billed at grok-4.3 rates, not the rates of the original model.

    Grok 4.1 Fast (Reasoning), Grok 4.1 Fast (Non-Reasoning), Grok 4 Fast (Reasoning), Grok 4 Fast (Non-Reasoning), Grok 4, Grok 3 to Grok 4.3 · xAI API ·

  • Defaults

    Reasoning slugs are served with low reasoning effort and non-reasoning slugs with none; set medium or high explicitly for deeper reasoning.

    Grok 4.1 Fast (Reasoning), Grok 4.1 Fast (Non-Reasoning), Grok 4 Fast (Reasoning), Grok 4 Fast (Non-Reasoning), Grok 4, Grok 3 to Grok 4.3 · xAI API ·

  • Parameters

    grok-4.20 and newer models silently ignore logprobs and top_logprobs.

    Grok 4.1 Fast (Reasoning), Grok 4.1 Fast (Non-Reasoning), Grok 4 Fast (Reasoning), Grok 4 Fast (Non-Reasoning), Grok 4, Grok 3 to Grok 4.3 · xAI API ·

Intelligence

Third-party results, credited below
Third-party benchmark scores for Grok 4.1 Fast (Reasoning)
BenchmarkPublisherScoreRankPublished
Arena TextArena1,430 ± 2#57 of 128Oct 8, 2026
Arena WebDevArena1,242 ± 6#63 of 69Oct 8, 2026

Arena (arena.ai), https://arena.ai/leaderboard

Change history

ShutdownGrok 4.1 Fast models shut down on Agent PlatformGoogle Vertex AI

Google stopped serving grok-4.1-fast-reasoning and grok-4.1-fast-non-reasoning through Model as a Service on Gemini Enterprise Agent Platform.

Platform
Google Vertex AI
Announced

Source: Google Cloud, Gemini Enterprise Agent Platform release notes (opens in a new tab); Google Cloud, Grok 4.1 Fast (opens in a new tab)

RedirectSix Grok models retired on the xAI API and redirected to Grok 4.3xAI API3 breaks

xAI retired grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning, grok-4-fast-reasoning, grok-4-fast-non-reasoning, grok-4-0709 and grok-3. The slugs still resolve: requests are served by grok-4.3 instead of returning an error.

Platform
xAI API
Replacement
Grok 4.3
  • PricingRequests to the retired slugs are billed at grok-4.3 rates, not the rates of the original model.
  • DefaultsReasoning slugs are served with low reasoning effort and non-reasoning slugs with none; set medium or high explicitly for deeper reasoning.
  • Parametersgrok-4.20 and newer models silently ignore logprobs and top_logprobs.

Source: xAI, Grok Model Retirement on May 15, 2026 (opens in a new tab); xAI, Models (opens in a new tab)

Built by TeqEngine. Forward-deployed AI engineering, no model to sell. Moving an agent to a new model? Ask for a Next-Model Check.