Providers · Beta

Keep Mistral API usage within workload limits.

Add a Mistral API key once. Give each app an approved chat or embedding model, a hard spending limit, and a fallback.

Create a free workspace Try the no-card Test Lab

How the connection works

How Mistral AI works with the gateway

Check access before inference

The connection test reads Mistral's documented model catalog with the encrypted provider credential. It does not send a prompt or generate tokens merely to prove the key can reach the account.

Match the route to the request

The adapter accepts Chat Completions and embeddings on their documented paths and rejects unsupported protocol boundaries. A model must be eligible for the workload's exact request type before it can become a target.

Add a separate workload ceiling

Each app receives a scoped gateway key, dollar budget, request rate, token rate, and concurrency limit. Mistral's Free or paid workspace limits still apply upstream.

Current shared controls

What every supported connection includes

Encrypted BYOK credentials that remain hidden after setup Stable model aliases and compatible route targets Organization and key budgets, rate limits, and concurrency limits Observe, Shadow, and Enforce modes with metadata-only evidence

Test the exact Mistral model, request type, streaming behavior, and workspace limits before production approval.

Client boundary

AIGHQ_BASE_URL=https://api.aigatewayhq.com/v1
AIGHQ_API_KEY=from-your-workspace
AIGHQ_MODEL=company-approved-fast

Applications use the gateway URL, a workload key, and a stable model alias. Administrators can change an eligible Mistral model or API key centrally without distributing the Mistral credential to every app.

Implemented boundary

Supported protocols

Select Mistral AI and enter a workspace-scoped API key. The connection test reads the model catalog and does not generate tokens. Then assign eligible chat or embedding models to stable aliases.

POST /v1/chat/completions OpenAI-compatible streaming POST /v1/embeddings GET /v1/models connection test

Compatibility follows the provider's current published interface. Review the provider documentation before approving Mistral AI for production.