AI & ML Bearer Token

Mistral AI REST API

Open-weight AI models with frontier-level performance

Mistral AI provides state-of-the-art large language models through a simple REST API. Developers use Mistral for chat completions, embeddings, and function calling with models like Mistral Large, Mistral Small, and open-weight alternatives. The API offers streaming responses, JSON mode, and tool integration for building AI-powered applications with competitive pricing and performance.

Base URL https://api.mistral.ai/v1

API Endpoints

Method	Endpoint	Description
POST	`/chat/completions`	Generate chat completions using Mistral models with support for streaming, function calling, and JSON mode
POST	`/embeddings`	Create vector embeddings from text using Mistral's embedding models for semantic search and RAG applications
GET	`/models`	List all available Mistral models with their capabilities, pricing, and context window sizes
POST	`/fim/completions`	Fill-in-the-middle completions for code generation and completion tasks with Codestral models
POST	`/agents/completions`	Execute agent workflows with function calling and tool use for autonomous task execution
GET	`/models/{model_id}`	Retrieve detailed information about a specific Mistral model including parameters and capabilities
POST	`/moderations`	Analyze content for policy violations, harmful content, and safety guardrails
POST	`/classifiers`	Classify text into predefined categories using Mistral's classification capabilities
GET	`/files`	List uploaded files used for fine-tuning and retrieval augmented generation
POST	`/files`	Upload files for fine-tuning datasets or document retrieval in RAG applications
DELETE	`/files/{file_id}`	Delete a previously uploaded file from Mistral storage
POST	`/fine_tuning/jobs`	Create a fine-tuning job to customize Mistral models on your specific dataset
GET	`/fine_tuning/jobs`	List all fine-tuning jobs with their status, metrics, and configuration
GET	`/fine_tuning/jobs/{job_id}`	Get detailed status and metrics for a specific fine-tuning job
DELETE	`/fine_tuning/jobs/{job_id}`	Cancel an in-progress fine-tuning job

Code Examples

curl https://api.mistral.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -d '{
    "model": "mistral-large-latest",
    "messages": [
      {
        "role": "user",
        "content": "What is the best French cheese?"
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

const response = await fetch('https://api.mistral.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': `Bearer ${process.env.MISTRAL_API_KEY}`
  },
  body: JSON.stringify({
    model: 'mistral-large-latest',
    messages: [
      {
        role: 'user',
        content: 'What is the best French cheese?'
      }
    ],
    temperature: 0.7,
    max_tokens: 1000
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

import os
import requests

response = requests.post(
    'https://api.mistral.ai/v1/chat/completions',
    headers={
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {os.environ["MISTRAL_API_KEY"]}'
    },
    json={
        'model': 'mistral-large-latest',
        'messages': [
            {
                'role': 'user',
                'content': 'What is the best French cheese?'
            }
        ],
        'temperature': 0.7,
        'max_tokens': 1000
    }
)

data = response.json()
print(data['choices'][0]['message']['content'])

Use Mistral AI from Claude / Cursor / ChatGPT

Get a hosted MCP endpoint for Mistral AI. Paste your Mistral AI API key, copy back one URL, drop it into Claude Desktop, Cursor, or any AI client that supports remote MCP. Your AI calls Mistral AI directly with your credentials — no local install, works on mobile.

mistral_chat Generate conversational responses using Mistral's chat models with context awareness and streaming support

mistral_embed Create semantic embeddings for text to enable similarity search, clustering, and retrieval augmented generation

mistral_function_call Execute structured function calls with Mistral models for tool use, API integration, and autonomous agents

mistral_code_complete Generate code completions and fill-in-the-middle suggestions using Codestral models for development workflows

mistral_moderate Analyze and classify content for safety, policy compliance, and harmful content detection with Mistral's moderation system

Connect in 60 seconds

Paste your Mistral AI key → get an MCP URL → paste into Claude/Cursor. Hosted by IOX, encrypted at rest.

Connect Mistral AI to your AI →

Mistral AI REST API

API Endpoints

Sponsor this page

Code Examples

Use Mistral AI from Claude / Cursor / ChatGPT

Connect in 60 seconds

Related APIs