Mistral Large 4 API

Q: What is the Mistral Large 4 model ID?

Use mistralai/mistral-large-4-0 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

Mistral AI's largest model to date: a 1 trillion-parameter natively multimodal Mixture of Experts with 49 billion active parameters and a 512K context window.

Modalities: Text, ImageText
In / Out price: $1.36/$4.18per 1M
Context window: 512K tokens
Released: Oct 6, 2026

Mistral Large 4 overview

Mistral Large 4 by Mistral AI

Mistral Large 4 is a 1 trillion-parameter natively multimodal model with 49 billion active parameters, built as a hybrid instruct-and-reasoning Mixture of Experts. It is served with a 512K context window and up to 256K output tokens.

Mistral Large 4 specs

Model ID: mistralai/mistral-large-4-0
Developer: Mistral AI
Context window: 524,288 tokens
Max output: 262,144 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is Mistral Large 4 API?

Mistral Large 4 is a 1 trillion-parameter natively multimodal model with 49 billion active parameters, built as a hybrid instruct-and-reasoning Mixture of Experts. Mistral describes it as its largest and most capable model to date, and the weights are open.

Technical Reference

Developer	Mistral AI
Model ID	mistralai/mistral-large-4-0
Modalities	Image, Text → Text
Context window	524,288 tokens
Max output	262,144 tokens
Parameters	1 trillion total, 49 billion active
Architecture	Hybrid instruct-and-reasoning Mixture of Experts
Released	6 October 2026

What Mistral Large 4 Brings to the Table

Sparse at scale
1 trillion parameters in total but 49 billion active per token, so capacity does not translate one-for-one into cost per request.

A 512K window
524,288 tokens in and up to 262,144 out, which fits an entire service, source, tests and a ticket thread, in one prompt.

Instruct and reasoning in one
A hybrid design rather than separate chat and reasoning checkpoints.

Native multimodality
Image input is built in rather than bolted on.

Vendor-Reported Benchmarks

Published by Mistral AI with the Mistral Large 4 announcement, retrieved 6 October 2026. These are the vendor's own figures and have not been independently reproduced.

Cybench: 93% on vulnerability reproduction and patching
Dense 200 (visual grounding): 42%

Where Mistral Large 4 Makes the Most Sense

Long-running agent work
The DeepSWE and AutomationBench figures are both about finishing multi-step tasks rather than answering one question.

Whole-repository reasoning
A 512K window keeps the context in the prompt instead of in a retrieval layer.

Sources: https://mistral.ai/news/mistral-large-4 · https://docs.mistral.ai/models/mistral-large-4-0

Use cases

Agentic software work: Mistral reports 61.7% on DeepSWE v1.1 and 59.9% on AutomationBench.
Security review: 93% on Cybench for vulnerability reproduction and patching.
Document and screenshot understanding: native image input, with 42% on Dense 200 visual grounding.
Self-hosting: open weights, for teams that need the model inside their own perimeter.

Mistral Large 4 benchmarks by Artificial Analysis

See how Mistral Large 4 compares in intelligence and cost per task. Data retrieved Nov 3, 2026.

Intelligence#28 / 5026Index v5.0 Cost per task#28 / 44$2.06USD / benchmark task Terminal-Bench 4.0#33 / 15424.7%Score

Intelligence

Index v5.0

Cost per task

USD / benchmark task

Benchmark results

Compare 5 models available on AI/ML API across 1 independent benchmark.

Terminal-Bench 4.0

Agentic tasks completed in a command-line environment.

Mistral Large 4 API pricing

Mistral Large 4 pricing in US dollars
Usage	Price	Unit
Input	$1.36	1M tokens
Output	$4.18	1M tokens
Cached input	$0.14	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Mistral Large 4 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Mistral Large 4	$1.36	$4.18
Small 4	$0.1984	$0.7935
Devstral 2 2512	$0.4655	$2.33
Sakana Namazu	$1.01	$4.23
Medium 3.5	$1.59	$7.93

How to use the Mistral Large 4 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "mistralai/mistral-large-4-0",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/mistral-large-4-0",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "mistralai/mistral-large-4-0",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Mistral Large 4 FAQ

What is Mistral Large 4?

How much does Mistral Large 4 cost?

Mistral Large 4 costs $1.36 input and $4.18 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Can Mistral Large 4 read images?

Yes. Mistral describes it as natively multimodal, taking both text and image input and returning text.

What benchmarks did Mistral publish for Mistral Large 4?

With the announcement Mistral reported DeepSWE v1.1 61.7%, Cybench 93% on vulnerability reproduction and patching, AutomationBench 59.9%, Dense 200 visual grounding 42%, B3 Attack Resistance 93.3%, and a KORA score of 1.691. These are the vendor's own figures, not independently reproduced.

Are Mistral Large 4 weights open?

Mistral describes the model as open-weight and said at announcement that the weights would drop at the end of the month.

What is the Mistral Large 4 model ID?

Use mistralai/mistral-large-4-0 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of Mistral Large 4?

Mistral Large 4 accepts up to 524,288 tokens of context and returns up to 262,144 output tokens.

Start building with Mistral Large 4

Get API key

Mistral Large 4 API

mistralai/mistral-large-4-0

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "mistralai/mistral-large-4-0",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "mistralai/mistral-large-4-0",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "mistralai/mistral-large-4-0",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Mistral Large 4 API

Mistral Large 4 overview

Mistral Large 4 by Mistral AI

Mistral Large 4 specs

What Is Mistral Large 4 API?

Technical Reference

What Mistral Large 4 Brings to the Table

Vendor-Reported Benchmarks

Where Mistral Large 4 Makes the Most Sense

Use cases

Mistral Large 4 benchmarks by Artificial Analysis

Intelligence

Cost per task

Benchmark results

Terminal-Bench 4.0

Mistral Large 4 API pricing

Mistral Large 4 vs other models: token prices

How to use the Mistral Large 4 API

Build with your agent

1Get your API key

2Make your first request

Related articles

Mistral Large 4 FAQ

Start building with Mistral Large 4

Mistral Large 4 API

Build with your agent

1Get your API key

2Make your first request

Mistral Large 4 API

Mistral Large 4 overview

Mistral Large 4 by Mistral AI

Mistral Large 4 specs

What Is Mistral Large 4 API?

Technical Reference

What Mistral Large 4 Brings to the Table

Vendor-Reported Benchmarks

Where Mistral Large 4 Makes the Most Sense

Use cases

Intelligence

Cost per task

Benchmark results

Terminal-Bench 4.0

Mistral Large 4 API pricing

Mistral Large 4 vs other models: token prices

How to use the Mistral Large 4 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Mistral Large 4

Mistral OCR 4

Mistral OCR 3

Medium 3.5

Muse Spark 1.3

Muse Spark Open

Muse Spark 1.1

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Mistral Large 4 FAQ

Start building with Mistral Large 4