Mistral Large 3

mistral-large-3 by Mistral AI Released August 13, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.5 / 1M
Output from
$1.5 / 1M
Cached input from
$ / 1M
Context window
256K
Endpoints
3
from 1 providers
Regions
Global, Europe, United States

About Mistral Large 3

Mistral Large 3 is a chat model by Mistral AI, available on Eden AI through 3 endpoints from 1 provider, from $0.5 per million input tokens and $1.5 per million output tokens, with a context window of up to 256K tokens.

Providers and prices

3 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
Microsoft AzureOfficial−%azure/mistral-large-3
Global
256K
$0.5$0.5
$1.5
$
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (Europe)Official−%azure/mistral-large-3@eu
Europe
256K
$0.55$0.55
$1.65
$
ReasoningToolsJSONCacheVisionWeb
Microsoft Azure (United States)Official−%azure/mistral-large-3@us
United States
256K
$0.55$0.55
$1.65
$
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
0.54 s
Microsoft Azure
Lowest latency
8.82 s
Microsoft Azure
Highest throughput
39.69 tok/s
Microsoft Azure
Best availability
100%
Microsoft Azure
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Microsoft Azure
0.54 s
8.82 s
69.61 s
39.69 tok/s
100%
0%
11.11%
6.98%
Microsoft Azure (Europe)
s
s
s
tok/s
%
%
%
%
Microsoft Azure (United States)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Mistral Large 3 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())

Questions about Mistral Large 3

On Eden AI, prices for this model start at $0.5 per million input tokens and $1.5 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 256K tokens, depending on the endpoint.

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

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.

Over the last 30 days, the fastest first token was 0.54 s (Microsoft Azure) and the highest throughput was 39.69 tokens per second (Microsoft Azure).