Loading the catalogue…
Loading the catalogue…
Same model, one lane, your call. Sovereign first, then European-hosted, then routed (typically non-EU). Default endpoint per lane is highlighted.
| Provider | Input / M | Output / M | Status |
|---|---|---|---|
MistralDefault | €2.00 | €5.00 | Active |
Stav speaks the same chat-completions API you already use. Set STAV_API_KEY and the curl below works. SDKs (openai-python, langchain, litellm) all work with the same base URL.
curl https://api.stav.ai/v1/chat/completions \
-H "Authorization: Bearer $STAV_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "magistral-medium-2509",
"messages": [{"role": "user", "content": "Hello!"}]
}'Prefer the Anthropic SDK contract? The same model is also reachable at POST /v1/messages — Stav's gateway translates between Anthropic-shape and the underlying provider for non-Claude models.
Sovereign-EU inference by default; the Smart Router lifecycle penalty drains traffic away from deprecating endpoints automatically. Add to attribute requests to a registered app.
X-Stav-App-Id: <uuid>Pick this model first.
Works — usually a fine pick.
Other models will serve you better.
Fit assertions set by the curator pipeline. 39 use cases mapped.
Model catalogue
Inference runs in FR on mistral. The data stays in EU at rest, but the provider's parent jurisdiction may carry compelled-disclosure obligations. Acceptable for many regulated workloads but does not satisfy the strictest sovereignty mandates.