Skip to content

xAI · Chat

Grok 4.20

xAI 🇺🇸ChatGrok familyOne of its sources says the weights aren't publicly available.The maker currently plans to deprecate it within the next 180 days (6 Apr 2027). Plans can change.
From Netmind's listing:
Grok 4.20 (0309, non-reasoning) is the low-latency non-reasoning variant of the Grok 4.20 family from xAI, with a 1M token context window, tool/function calling, and multimodal text and image input. It is tuned for fast responses without extended reasoning.
llminfo IQ
129.3
Max context
2M
Listings
96

Evidence and sources

llminfo IQ 129.3, ranked among chat models. From 281 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 108.2, 95% interval 101–116. From 11 benchmark families across 7 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (40.6). Costs more per task than its benchmark results predict. From 30 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (45 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 22,619 output tokens per task at default effort.How the Yap score worksReleased 17 Feb 2026 Training-data cutoff, as its sources state it Maker HQ: US (according to xAI's own website)
All rankings: #113 on NanoGPT recently #158 on OpenRouter today #175 on OpenRouter this week #176 on OpenRouter this monthSources: LMArena data, Venice.ai data, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, NetMind.AI, llminfo researchPrimary data from LMArena from Venice.ai: name from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from NetMind.AI: description from llminfo research: release date

Advantages and trade-offs

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

Advantages

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 6 Apr 2027, within the next 180 days.

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, 04:34 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; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb searchBatch API

Listings

 xAIgrok-4.20Sources: GenAI Prices data, LiteLLM data1M$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.00$1.25
 Tokenlabgrok-4.20-non-reasoning · non-reasoningSource: Models.dev data1M$0.625cache read $0.10$1.25—
 Vercelspacexai/grok-4.20-non-reasoning-batch · batch, non-reasoningSource: Vercel AI Gateway data2M$1.00cache read $0.16$2.00—
 Microsoft Azureazure_ai/grok-4-20-non-reasoning · non-reasoningSources: LiteLLM data, Models.dev data262K$1.25$2.50—
 Googlevertex_ai/xai/grok-4.20-non-reasoning · non-reasoningSources: LiteLLM data, Models.dev data2M$1.25>200k $2.50cache read $0.20$2.50>200k $5.00—
 Cometapigrok-4.20-0309-reasoning · reasoning, 0309Sources: CometAPI data, CometAPI Pricing dataNot published by the provider$1.25$2.50—
 Eden AIInference by xAIxai/grok-4.20-0309-non-reasoning · non-reasoning, 0309Source: Models.dev data1M$1.25cache read $0.20$2.50—
 Fastrouterx-ai/grok-4.20-beta · betaSource: FastRouter data2M$1.25>200k $2.50cache read $0.20batch $1.00$2.50>200k $5.00batch $2.00—
 Kilox-ai/grok-4.20Sources: Kilo AI Gateway data, Models.dev data2M$1.25cache read $0.20$2.50—
 Llmgatewaygrok-4-20-non-reasoning · non-reasoningSource: LLMGateway data2M$1.25cache read $0.20$2.50—
Show all 82 listings

Showing 10 of 82: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Aihubmix, Aimlapi, Cloudflare AI Gateway, Flowdot, Impossibl, Llmgateway Providers, Merge Gateway, NanoGPT, Netmind, Nous Portal, Oci, Ofox, OpenRouter, Perplexity, Tokenmix, Venice, Wavespeed.

14 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 ELO64 related benchmarks · 64 results
Source: LMArena data · Nov 2026
BenchmarkReasoning, 0309, beta
Arena ELO
Chinese
Creative Writing
Document
Show 60 more benchmarksHide 60 benchmarks
BenchmarkReasoning, 0309, beta
Document Style-Controlled
English
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
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
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - German
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Entity Recognition
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Reasoning

Coding

Arena ELOSource: LMArena data · Nov 2026
ValsSource: Vals AI

Long context

Agentic

Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

General

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs

Math

Vision

Instruction following

Knowledge

Science

Factuality

OCR

Other

ArmBench-LLM Armenian22 related benchmarks · 22 results
Horangi36 related benchmarks · 72 results
Nejumi 428 related benchmarks · 28 results
Vals10 related benchmarks · 12 results
EMB
Source: Vals AI
CaseLaw v2
Source: Vals AI
CorpFin v2
Source: Vals AI
LegalBench
Source: Vals AI
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
Show 5 more resultsHide 5 results
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MortgageTax
Source: Vals AI

Data credits: 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. · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · 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) · Data by LLM Stats · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results

Also known as: aihubmix/grok-4-20-non-reasoning, aihubmix/grok-4-20-reasoning, azure_ai/grok-4-20-non-reasoning, azure_ai/grok-4-20-reasoning, grok-4-20, grok-4-20-beta-0309-non-reasoning, grok-4-20-beta-0309-reasoning, grok-4-20-non-reasoning, grok-4-20-reasoning, grok-4.20-0309-non-reasoning, grok-4.20-0309-reasoning, grok-4.20-beta, grok-4.20-beta-0309-non-reasoning, grok-4.20-beta-0309-reasoning, grok-4.20-beta-reasoning-0309, grok-4.20-non-reasoning, grok-4.20-reasoning, grok-4.20:web, oci/xai.grok-4.20, oci/xai.grok-4.20-0309-non-reasoning, oci/xai.grok-4.20-0309-reasoning, oci/xai.grok-4.20-non-reasoning, oci/xai.grok-4.20-reasoning, perplexity/xai/grok-4.20-non-reasoning, perplexity/xai/grok-4.20-reasoning, spacexai/grok-4.20-non-reasoning, spacexai/grok-4.20-non-reasoning-batch, spacexai/grok-4.20-non-reasoning-beta, spacexai/grok-4.20-reasoning, spacexai/grok-4.20-reasoning-batch, spacexai/grok-4.20-reasoning-beta, vertex-openai/grok-4-20-non-reasoning, vertex-openai/grok-4-20-reasoning, vertex_ai/xai/grok-4.20-non-reasoning, vertex_ai/xai/grok-4.20-reasoning, x-ai/grok-4-20-0309-non-reasoning, x-ai/grok-4-20-0309-reasoning, x-ai/grok-4.20, x-ai/grok-4.20-0309-non-reasoning, x-ai/grok-4.20-0309-reasoning, x-ai/grok-4.20-beta, x-ai/grok-4.20-non-reasoning, x-ai/grok-4.20-non-reasoning-beta, x-ai/grok-4.20-reasoning, x-ai/grok-4.20-reasoning-beta, xai.grok-4.20-non-reasoning, xai.grok-4.20-reasoning, xai/grok-4-20-beta-0309-non-reasoning, xai/grok-4-20-beta-0309-reasoning, xai/grok-4-20-non-reasoning, xai/grok-4.20, xai/grok-4.20-0309, xai/grok-4.20-0309-non-reasoning, xai/grok-4.20-0309-reasoning, xai/grok-4.20-beta, xai/grok-4.20-beta-0309, xai/grok-4.20-beta-0309-non-reasoning, xai/grok-4.20-beta-0309-reasoning, xai/grok-4.20-beta-latest, xai/grok-4.20-beta-latest-non-reasoning, xai/grok-4.20-beta-latest-reasoning, xai/grok-4.20-beta-non-reasoning, xai/grok-4.20-beta-reasoning, xai/grok-4.20-non-reasoning, xai/grok-4.20-non-reasoning-latest, xai/grok-4.20-reasoning, xai/grok-4.20-reasoning-latest

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