Providers · Beta

Put Mistral models behind a stable workload boundary.

First-class Mistral BYOK with a fixed official host, zero-inference model-catalog verification, Chat Completions, and embeddings eligibility.

Start in a test environment Read current API behavior

How the connection works

Provider access stays separate from application control.

Verify access without generating text

The connection check reads Mistral's documented model catalog with the write-only provider credential. It does not send a prompt or create inference usage merely to prove the key can reach the account.

Keep chat and embeddings distinct

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

Change the provider key once

Applications receive scoped AI Gateway HQ workload keys rather than the Mistral credential. Administrators can rotate or pool upstream access while preserving each workload's route, dollar budget, rate, concurrency, and audit boundary.

Current shared controls

Status determines what can be configured.

Write-only, encrypted BYOK for implemented provider connections Stable model aliases and protocol-eligible route targets Organization and key budgets, RPM, TPM, and concurrency hard limits Observe, Shadow, Enforce, reason codes, and metadata-only evidence

Beta connections require customer validation against the exact model, payload, streaming mode, region, and provider account before production use.

Client boundary

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

Applications keep a stable gateway URL and model alias while an administrator changes eligible provider accounts and models.

Implemented boundary

Only documented protocols become eligible.

Choose Mistral AI, enter the write-only API key, verify the model catalog, and add only chat or embedding models to the route.

POST /v1/chat/completions POST /v1/embeddings GET /v1/models connection test

Compatibility is bounded to the provider's current published interface. Review the provider documentation before approving a production model.