Enterprise DNAEnterprise DNA
Mistral logo

Models · Best vision

Mistral Large 4

by Mistral

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

Visit Mistral ↗

Our verdict

Not reviewed yet

We have not reviewed Mistral Large 4 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Mistral Large 4

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

Best for

Multimodal engineering workflows

Notes

Mistral Large 4 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Analysing text and image evidence together
  • text, image input; text output on the listed OpenRouter route

Cons

  • Assuming a provider comparison proves your task outcome
  • Equating accessible weights with unrestricted use
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Key facts

What we have checked

Input price
$0.700 per million tokens
Checked OpenRouter models API
Output price
$2.10 per million tokens
Checked OpenRouter models API
Price on mistralai
$0.070 per million cached input tokens
Checked OpenRouter models API
Price on mistralai
$0.700 per million input tokens
Checked OpenRouter models API
Price on mistralai
$2.10 per million output tokens
Checked OpenRouter models API
Latest version
mistralai/mistral-large-4-0-20261006
Checked OpenRouter models API
Time to first token (ms)
1,420
Checked Artificial Analysis
Time to first token (ms) on mistralai
1,255
Checked OpenRouter models API
Output speed (tokens a second)
161.3
Checked Artificial Analysis
Gpqa diamond
88.1% (for 6 Oct 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
58.6% (for 6 Oct 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
20% (for 6 Oct 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `mistralai/mistral-large-4-0`.

  • openrouter · mistralai/mistral-large-4-0 · Docs

OpenRouter id: mistralai/mistral-large-4-0

Price

What Mistral Large 4 costs, over time

Input price

$0.680 to $0.700

US dollars per million input tokens. 6 Oct 2026 to 28 Oct 2026, 20 days.

Source: OpenRouter models API. Checked .

Output price

$2.09 to $2.10

US dollars per million output tokens. 6 Oct 2026 to 28 Oct 2026, 20 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
mistralaiCached input$0.070 per million cached input tokensSince 29 Oct 20261 changeOpenRouter models API
mistralaiInput$0.700 per million input tokensSince 29 Oct 20261 changeOpenRouter models API
mistralaiOutput$2.10 per million output tokensSince 29 Oct 20261 changeOpenRouter models API

Usage

How much Mistral Large 4 is used

Tokens served a day

12.7B to 21.9B

tokens a day on OpenRouter. 6 Oct 2026 to 28 Oct 2026, 23 readings.

Source: OpenRouter model activity (728 of 728 series). Checked .

Scores

How Mistral Large 4 scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index25.3indexAs of 28 Oct 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,430EloAs of 28 Oct 2026LMArena (CC-BY-4.0), published 2026-10-28
LMArena web development rating (Elo)1,544EloAs of 28 Oct 2026LMArena (CC-BY-4.0), published 2026-10-28
LMArena vision rating (Elo)1,272EloAs of 28 Oct 2026LMArena (CC-BY-4.0), published 2026-10-28
Design Arena rating (Elo)1,275EloAs of 28 Oct 2026Design Arena via OpenRouter
Chess puzzles (best-across-versions)33percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)88.2percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)39.4percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)26.8percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)58.6percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Furniture assembly (best-across-versions)20.8percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)88.1percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Show 7 more scores
ScoreValueSourceChecked
Lmca (best-across-versions)35.8percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)17percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated98.3percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)10percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)20percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Surface evolver bench (best-across-versions)28.1percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Weirdml v3 (best-across-versions)12.2percentAs of 6 Oct 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.14 to 0.07

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 4.18 to 2.1

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 1.36 to 0.7

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 4.18 to 2.1

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 1.36 to 0.7

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 2.09 to 4.18

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.68 to 1.36

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Mistral Large 4 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
162B ▼6.3%
Requests, last 7 days
2.2M
Tool calls, last 7 days
1M
Intelligence score
25.3
People's vote
1430
Average cost per request
$5.82
Price per million tokens
$0.7 in · $2.1 out
050B100B6 Oct: 12.7B tokens, 349K requests7 Oct: 27.1B tokens, 540K requests8 Oct: 18B tokens, 487K requests9 Oct: 20.6B tokens, 472K requests10 Oct: 10.6B tokens, 375K requests11 Oct: 14.3B tokens, 256K requests12 Oct: 58.4B tokens, 693K requests13 Oct: 44B tokens, 437K requests14 Oct: 32.3B tokens, 369K requests15 Oct: 16.2B tokens, 437K requests16 Oct: 20.2B tokens, 430K requests17 Oct: 12.7B tokens, 267K requests18 Oct: 17.6B tokens, 323K requests19 Oct: 26.6B tokens, 432K requests20 Oct: 35.4B tokens, 481K requests21 Oct: 43.6B tokens, 543K requests22 Oct: 78B tokens, 602K requests23 Oct: 16.5B tokens, 335K requests24 Oct: 5.1B tokens, 115K requests25 Oct: 5.7B tokens, 157K requests26 Oct: 6B tokens, 142K requests27 Oct: 28.3B tokens, 331K requests28 Oct: 21.9B tokens, 490K requests6 Oct20 Oct28 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Mistral Large 4.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-29. Hosting routes and app features can differ.

DeveloperMistral AI
Exact model identifiermistralai/mistral-large-4-0
Inputtext, image
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Custom licence, open weights
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
6 Oct 2026
Listed retirement date
Not established

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Analysing text and image evidence together
  • Preparing a scoped reasoning or coding response

Watch for

  • Assuming a provider comparison proves your task outcome
  • Equating accessible weights with unrestricted use

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Review this invoice arithmetic: subtotal 80, discount 10, tax 15%, claimed total 82.50. State the assumed discount order and calculate the corrected total.

Check the result: Under discount-before-tax the total is 80.50; alternate order is stated as a different assumption.

Compare another approach

anthropic claude sonnet 5 5 ↗openai gpt 6 1 sol ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

mistralai/mistral-large-4-0: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-29
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-10-29
Licence source ↗

Licence declared in the mistralai/Mistral-Large-4-1T-A52B model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-10-29
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 28 Oct 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 25.3 (2026-10-27) ↗Design Arena: 1275 (2026-10-27) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →