Mistral AI
Generate AI responses with Mistral. Fast, efficient European AI models. Chat, analysis, code generation, and more.
🔑 Setup Required — Bring Your Own Key
This integration requires API credentials. Store them once via
setup_integration or the Dashboard Vault — they're encrypted
with AES-256-GCM and never exposed.
Required Credentials
mistral_api_key
API Key
API key from console.mistral.ai → API Keys.
Get your API key at mistral.ai →
Endpoints (2)
POST
chat-completion
Send a conversation to Mistral and get an AI response. Supports system prompts and multi-turn conversations.
| Field | Type | Required | Description |
|---|---|---|---|
model |
string | ✓ Yes | Mistral model: "mistral-large-latest" (most capable), "mistral-medium-latest" (balanced), "mistral-small-latest" (fast/cheap), "open-mistral-nemo" (open-source). |
messages |
array | ✓ Yes | Conversation messages. Example: [{"role": "user", "content": "Explain quantum computing"}]. |
max_tokens |
integer | No | Max response tokens. Default: model-dependent. |
GET
list-models
List available Mistral models with their capabilities.
No input parameters required.
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| chat-completion | mistral_chat_completion |
| list-models | mistral_list_models |