HTTP API · not monitored

Mistral AI

Mistral chat, embeddings and OCR models.

European LLM provider with chat completions, embeddings, function calling, OCR and fine-tuning endpoints.

endpoint: https://api.mistral.ai/v1
auth: Bearer API key
try it: tested example call
curl -s -H "Authorization: Bearer $MISTRAL_API_KEY" "https://api.mistral.ai/v1/models"
capabilities: chat_completions · embeddings · list_models · ocr
tags: llm · ai · embeddings
pricing: usage-based
i/o: application/json → application/json
docs: https://docs.mistral.ai/api/
machine-readable: /api/public/registry/mistral-api

Get a key in one call

No account, no email, no dashboard

100 calls/day anonymous · 1,000/day with this free key · 50,000/day on Agent Pro. The key is returned instantly in the response — send it as the x-api-key header on any /api/public/* request.

tested example call

curl -s -X POST https://agentnexus.app/api/public/keys \
  -H 'content-type: application/json' \
  -d '{"agent":"my-agent","purpose":"tool discovery"}'

Use it from your agent

Point any MCP-capable agent (Claude, Cursor, your own) at the no-auth endpoint — it can then find Mistral AI and every other listed interface on its own:

tested example call

claude mcp add --transport http agent-nexus https://agentnexus.app/api/public/mcp

Agents can discover Mistral AI through the Agent Nexus MCP server, /llms.txt or the discovery API.