Skip to content

Mistral AI · Chat

Mistral Large 4

Mistral AI 🇫🇷ChatMistral familyOne of its sources says the weights aren't publicly available.The maker currently lists 27 Oct 2027 as the deprecation date. Plans can change.
From Cortecs AI's listing:
Mistral Large 4 is a trillion-parameter multimodal MoE model built for frontier-level reasoning, enterprise workloads, and multilingual applications, with 49B active parameters per token.
llminfo IQ
129.6
Maker's price
$1.05 blended / 1M
Max context
1M
Listings
28

Evidence and sources

🤗 mistralai/Mistral-Large-4-1T-A52Bllminfo IQ 129.6, ranked among chat models. From 173 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 114.7, 95% interval 108–122. From 14 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 (30.8). Costs more per task than its benchmark results predict. From 34 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 resultsChatty (62 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. By effort: default 62 · max 59.Median 103,988 output tokens per task at default effort.How the Yap score worksReleased 6 Oct 2026Maker HQ: FR (according to Mistral AI's own website)
All rankings: #91 on OpenRouter this week #93 on OpenRouter this month #105 on NanoGPT recently #118 on OpenRouter todaySources: LMArena data, LiteLLM data, Models.dev data, AI/ML API data, Cortecs EU Router data, llminfo researchPrimary data from LMArena from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from Cortecs EU Router: description from llminfo research: release date
Tags from its sources:instructtoolsvisionreasoningflagshipmoelong-contextfunction-callingprompt-caching

Advantages and trade-offs

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

Advantages

Trade-offs

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.

Input & output

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

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Mistral AImistral/mistral-large-4Sources: LiteLLM data, Models.dev data1M$0.70cache read $0.07$2.10——
 Flowdotmistral-large-4Source: FlowDot data256K$0.50$1.50——
 NanoGPTmistralai/mistral-large-4Sources: Models.dev data, NanoGPT524K$0.68cache read $0.07$2.09——
 Ollamamistral-large-4Source: Models.dev data1M$0.68cache read $0.07$2.09——
 Standardcomputemistralai/mistral-large-4-0Source: Models.dev data1M$0.68cache read $0.07$2.09——
 Microsoft Azureazure_ai/mistral-large-4-latest · latestSource: LiteLLM data1M$0.70$2.10——
 Kilomistralai/mistral-large-4-0Sources: Kilo AI Gateway data, Models.dev data1M$0.70cache read $0.07$2.10——
 Nous Portalmistralai/mistral-large-4-0Source: Nous Portal Inference Gateway data1M$0.70cache read $0.07$2.10——
 OpenRouterInference by Mistral AImistralai/mistral-large-4-0 · zdrSource: OpenRouter data docs1M$0.70cache read $0.07$2.1081863ms
 Vercelmistral/mistral-large-4Sources: Models.dev data, Vercel AI Gateway data1M$0.70cache read $0.07$2.10——
Show all 24 listings

Showing 10 of 24: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aihubmix, Cloudcode, Commandcode, Cortecs AI, Eden AI, Eurouter, Llmgateway, Llmgateway Providers, Lowrouter, Wavespeed, Zenmux.

4 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 ELO47 related benchmarks · 47 results
Source: LMArena data · Nov 2026
BenchmarkScore
Arena ELO
Chinese
Creative Writing
English
Show 43 more benchmarksHide 43 benchmarks
BenchmarkScore
Exclude Ties
Expert
French
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
Longer Query
Multi Turn
Non English
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
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 Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Russian
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

General

Agentic

Arena AgentSource: LMArena data

Coding

Arena ELOSource: LMArena data · Nov 2026
CyBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CyberGymSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SciCodeSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Reasoning

Multilingual

EKI EstonianSource: Keelemudelite mõõdupuu data docs · Oct 2026

Math

Science

Instruction following

Vision

Factuality

OCR

Other

Artificial Analysis10 related benchmarks · 10 results
Briefcase
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 4 more resultsHide 4 results
Dense200Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Data by LLM Stats · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · 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) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.

Also known as: azure_ai/mistral-large-4-latest, mistral-large-4-0, mistral-large-4@eu, mistral/mistral-large-4, mistral/mistral-large-4-0, mistral/mistral-large-4@eu, mistralai/mistral-large-4, mistralai/mistral-large-4-0

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