mistral.ai
Mistral AI provides language models and related products for building AI applications, plus Vibe and Studio products for coding assistants, agents, and API access. Its platform supports hosted model inference and developer tooling for integrating those capabilities into applications and workflows.
Mistral exposes a bearer-token authenticated HTTP API at https://api.mistral.ai/v1 and a Python-distributed `vibe` CLI for Vibe Code; no public GraphQL API, MCP server endpoint, or machine-readable OpenAPI spec URL was found in the docs searched.
- Mistral HTTP APIdiscovered
- Vibe CLIdiscovered
Create a key in Studio API Keys or via the Activate Studio and generate an API key quickstart: open the Studio console, go to API Keys, click Create new key, choose its name/expiration/scope, then copy the key immediately. For Vibe CLI users on Mistral plans, docs also point to Code › Vibe CLI as a key-generation path.
conventions · 1/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✓https://mistral.ai/llms.txt
- API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing