Mistral Large 4

mistral-large-4 by Mistral AI Released October 7, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 50% off

Input from

$0.68 / 1M

Output from

$2.09 / 1M

Cached input from

$0.07 / 1M

Context window

1.05M

Endpoints

from 1 providers

Regions

Europe

About Mistral Large 4

Mistral Large 4 est un modèle multimodal de pointe (saisie de texte et d'images) développé par Mistral AI et conçu pour le raisonnement, la programmation et les tâches impliquant des agents.

Mistral Large 4 est un modèle conversationnel développé par Mistral AI, disponible sur Eden AI via 2 endpoints chez 1 fournisseur, à partir de 0,68 $ par million de tokens en entrée et 2,09 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

2 endpoints from 1 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint

Region

Context

Input / 1M

Output / 1M

Cached / 1M

Supports

Mistral AI (Europe)Official−50%mistral/mistral-large-4-0

Europe

1.05M

$1.36$0.68

$2.09

$0.07

ReasoningToolsJSONCacheVisionWeb

Mistral AI (Europe)Official−%mistral/mistral-large-4

Europe

524K

$0.68$0.68

$2.09

$0.07

ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token

1.42 s

Mistral AI (Europe)

Lowest latency

2.45 s

Mistral AI (Europe)

Highest throughput

49.59 tok/s

Mistral AI (Europe)

Best availability

98.85%

Mistral AI (Europe)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Mistral AI (Europe)

1.42 s

2.45 s

51.92 s

49.59 tok/s

98.85%

89.26%

1.93%

0.75%

Mistral AI (Europe)

2.55 s

5.38 s

57.23 s

31.64 tok/s

98.4%

91.18%

3.84%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Mistral Large 4 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about Mistral Large 4

How much does Mistral Large 4 cost?

On Eden AI, prices for this model start at $0.68 per million input tokens and $2.09 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of Mistral Large 4?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve Mistral Large 4?

2 endpoints from 1 providers, available in: Europe. All of them are called with the same Eden AI API key.

Can I run Mistral Large 4 in the EU?

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

How fast is Mistral Large 4?

Over the last 30 days, the fastest first token was 1.42 s (Mistral AI (Europe)) and the highest throughput was 49.59 tokens per second (Mistral AI (Europe)).

About Mistral Large 4

Providers and prices

Performance

Estimate your monthly cost

Call Mistral Large 4 with Eden AI

Questions about Mistral Large 4

More from Mistral AI