How to Connect Mistral AI to an AI Agent
Auth setup
1. Sign up at console.mistral.ai. 2. Generate API key. 3. Use with OpenAI SDK (change base_url) or Mistral SDK.
Key facts
| Base URL | https://api.mistral.ai/v1/ |
|---|
| API version | v1 (OpenAI-compatible) |
|---|
| Auth | API key as Bearer token. Generate at console.mistral.ai. OpenAI SDK compatible. |
|---|
| Request body | application/json |
|---|
| Pagination | N/A — streaming via SSE. |
|---|
| Rate limit | Free tier: 1 req/sec, 500K tokens/month. Paid plans: higher. Check X-RateLimit headers. |
|---|
| Error format | JSON: {"object":"error","message":"...","type":"...","param":null,"code":null} |
|---|
Key endpoints
| Method | Path | Description |
|---|
POST | /chat/completions | Chat completion |
POST | /embeddings | Generate embeddings |
GET | /models | List models |
POST | /fim/completions | Fill-in-the-middle code completion |
Quickstart
POST /v1/chat/completions
Authorization: Bearer {api_key}
{"model":"mistral-large-latest","messages":[{"role":"user","content":"Hello"}]}
Agent pitfalls & tips
- OpenAI SDK compatible — change base_url to https://api.mistral.ai/v1.
- Mistral Large for quality, Mistral Small for speed, Codestral for code.
- FIM (fill-in-middle) endpoint is unique to Mistral — great for code infilling.
- JSON mode: set response_format={"type":"json_object"} for structured output.
- Function calling: use tools array, similar to OpenAI format.
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-04-07. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is Mistral AI's AEO score?
▼
Mistral AI has an AEO score of 0.70 and is rated A (Functional agent integration). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is Mistral AI AI-agent-ready?
▼
Mistral AI is currently connectable for AI agent use. API access is available but no dedicated MCP server has been published yet. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does Mistral AI compare to other AI & ML services?
▼
In the AI & ML category, Mistral AI is rated A. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how Mistral AI compares.
How can I integrate Mistral AI with an AI agent?
▼
The fastest way to integrate Mistral AI with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with Mistral AI?
▼
API key as Bearer token. Generate at console.mistral.ai. OpenAI SDK compatible. Setup: 1. Sign up at console.mistral.ai. 2. Generate API key. 3. Use with OpenAI SDK (change base_url) or Mistral SDK.
What are Mistral AI's API rate limits?
▼
Free tier: 1 req/sec, 500K tokens/month. Paid plans: higher. Check X-RateLimit headers.