Skip to content

xAI · Chat

Grok 4 Fast

xAI 🇺🇸ChatGrok familyOne of its sources says the weights aren't publicly available.The maker lists this model as deprecated (1 May 2026).

Newer version: Grok 4.2 Fast. Our catalogue has no release date for Grok 4.2 Fast. We compared the version names in our catalogue.

From Aiml API's listing:
Grok 4 Fast without reasoning for faster responses and lower latency.
llminfo IQ
122.2
Maker's price
$0.275 blended / 1M
Max context
2M
Listings
28

Evidence and sources

llminfo IQ 122.2, ranked among chat models. From 239 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 91.0, 95% interval 75–107. From 9 benchmark families across 6 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (65.9). Cheaper per task than its benchmark results predict. From 22 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 19 Sep 2025Maker HQ: US (according to xAI's own website)
Sources: LMArena data, LiteLLM data, Models.dev data, AI/ML API data, llminfo researchPrimary data from LMArena from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (1 May 2026).

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 9 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction calling

Listings

 xAIgrok-4-fast-non-reasoning · non-reasoningSource: GenAI Prices data2M$0.20cache read $0.05$0.50
 Jiekougrok-4-fast-non-reasoning · non-reasoningSource: Models.dev data2M$0.18$0.45
 Microsoft Azureazure_ai/grok-4-fast-non-reasoning · non-reasoningSource: LiteLLM dataNot published by the provider$0.20$0.50
 302aigrok-4-fast-non-reasoning · non-reasoningSources: 302.ai data, Models.dev data128K$0.20$0.50
 Eden AIInference by xAIxai/grok-4-fast-non-reasoning · non-reasoningSource: Models.dev data2M$0.20cache read $0.05$0.50
 Flowdotx-ai/grok-4-fastSource: FlowDot data2M$0.20$0.50
 OpenRouterx-ai/grok-4-fastSource: GenAI Prices data2M$0.20>128k $0.40cache read $0.05$0.50>128k $1.00
 RequestyInference by xAIxai/grok-4-fastSource: Requesty data2M$0.20>128k $0.40cache read $0.05$0.50>128k $1.00cache write $0.20
 Abacusgrok-4-fast-non-reasoning · non-reasoningSource: Models.dev data2M$0.20$0.50
 Poexai/grok-4-fast-non-reasoning · non-reasoningSource: Models.dev data2M$0.20cache read $0.05$0.50
Show all 19 listings

Showing 10 of 19: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Oci.

9 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO44 related benchmarks · 68 results
Source: LMArena data · Nov 2026
Arena ELO
Chinese
Creative Writing
English
Exclude Ties
Expert
Show 56 more resultsHide 56 results
French
German
Hard Prompts
Hard Prompts English
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian

Multilingual

IndicParam42 related benchmarks · 42 results
Show 36 more resultsHide 36 results

Coding

ValsSource: Vals AI

Agentic

Long context

Reasoning

General

Math

HMMT 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

Safety

PhareSource: Phare

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

SimpleQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

Vision

Other

ArmBench-LLM Armenian22 related benchmarks · 22 results
Horangi36 related benchmarks · 72 results
Vals7 related benchmarks · 11 results
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
clinical-result-2026, reasoning
clinical-result-2047, non-reasoning
Source: Vals AI
Setting not stated
CaseLaw v2
Source: Vals AI
CorpFin v2
Source: Vals AI
LegalBench
Source: Vals AI
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
clinical-result-2188, reasoning
clinical-result-2195, non-reasoning
Source: Vals AI
Setting not stated
MortgageTax
Source: Vals AI
Show 1 more resultHide 1 result
TaxEval v2
Source: Vals AI

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArmBench-LLM by Metric-AI. Public numeric primary task results; no separate results licence asserted. · CyBench — cite Zhang et al. 2025 · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Maheshwari et al., IndicParam, arXiv:2512.00333v3. Cited numeric scores under the owner's 2026-10-10 task-only restriction scope decision; no results licence established. Tasks, prompts and generations excluded. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Phare (Giskard), CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Around the web

  • Grok 4: The World's Most Powerful AI Model | xAI
    Grok 4: The World's Most Powerful AI Model · xAI Experience Grok 4, the revolutionary …Grok 4: The World's Most Powerful AI Model · xAI Experience Grok 4, the revolutionary AI model by xAI that delivers PhD-level intelligence across all subjects. With multi-agent collaboration, advance…

    grok4.me

  • The xAI Grok 4 model is now available on OCI | ai-data-science
    Oracle AI & Data Science Blog Follow: RSS Facebook Twitter LinkedIn YouTube Instagram Facebook Twitter …Oracle AI & Data Science Blog Follow: RSS Facebook Twitter LinkedIn YouTube Instagram Facebook Twitter LinkedIn Email Oracle AI The xAI Grok 4 model is now available on OCI Highlights of these update…

    blogs.oracle.com

  • xAI Releases Grok 4 Fast with Lower Cost Reasoning Model - InfoQ
    Reading list xAI has introduced Grok 4 Fast , a new reasoning model designed for …Reading list xAI has introduced Grok 4 Fast , a new reasoning model designed for efficiency and lower cost. The model reduces average thinking tokens by 40% compared with Grok 4, which brings an esti…

    infoq.com

  • Musk unveils Grok 4 as xAI’s new AI model that beats OpenAI and Google on major benchmarks
    several benchmarks, Grok 4 now leads the field, surpassing OpenAI, Google, Anthropic, and Deepseek. This …several benchmarks, Grok 4 now leads the field, surpassing OpenAI, Google, Anthropic, and Deepseek. This is the first time an xAI model has taken the top spot. Grok 4 also performs best in the SWE-Be…

    the-decoder.com

  • Elon Musk confirms xAI's Grok 4 launch for July 9: Where to watch, features | Tech News - Business Standard
    Elon Musk has confirmed that Grok 4, the latest AI language model from his artificial …Elon Musk has confirmed that Grok 4, the latest AI language model from his artificial intelligence venture xAI , will launch on July 9. The announcement was made via a post on X (formerly Twitter), w…

    business-standard.com

  • Grok 4 spotted ahead of launch with special coding features
    July 2, 2025 08:22 AM 0 Grok Elon Musk-funded xAI is skipping Grok 3.5 and …July 2, 2025 08:22 AM 0 Grok Elon Musk-funded xAI is skipping Grok 3.5 and releasing Grok 4 after Independence Day in the United States, and it could be the best model from the company. Grok 3.5 was …

    bleepingcomputer.com

  • Grok 4: Model Specifications and Details
    Contact Compute Efficiency Content Integrity Terms of Use Privacy Policy Cookie Preferences APX AI Online …Contact Compute Efficiency Content Integrity Terms of Use Privacy Policy Cookie Preferences APX AI Online I can see the page you're looking at. Ask me anything! Chat Grok 4: Model Specifications and …

    apxml.com

  • Grok 4 Fast | SpaceXAI
    We're rolling out Grok 4 Fast as two models: grok-4-fast-reasoning and grok-4-fast-non-reasoning , each with …We're rolling out Grok 4 Fast as two models: grok-4-fast-reasoning and grok-4-fast-non-reasoning , each with a 2M token context window. This allows developers to tune the amount of test-time compute …

    x.ai

  • Grok 4 is coming: Elon Musk confirms launch date, livestream details | Mint
    Aman Gupta Published 8 Jul 2025, 09:26 AM IST Elon Musk has confirmed that Grok …Aman Gupta Published 8 Jul 2025, 09:26 AM IST Elon Musk has confirmed that Grok 4 will launch this week AI Quick Read Elon Musk has confirmed that the latest version of xAI's Grok language model will…

    livemint.com

Also known as: azure_ai/grok-4-fast-non-reasoning, azure_ai/grok-4-fast-reasoning, grok-4-fast-non-reasoning, grok-4-fast-reasoning, grok-4-fast-search, oci/xai.grok-4-fast, x-ai/grok-4-fast, x-ai/grok-4-fast-non-reasoning, x-ai/grok-4-fast-reasoning, xai/grok-4-fast, xai/grok-4-fast-non-reasoning, xai/grok-4-fast-reasoning

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works