Loading the catalogue…
Mistral AI's open-weight flagship: a 675B-parameter (41B active) Granular MoE model with native vision input, function calling, and a 262,144-token context window, built for long-document and multimodal workflows.
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 | TTFT | Tok/s | Reliability | Status |
|---|---|---|---|---|---|---|
MistralDefault | €0.43 | €1.29 | 0.25 s | 89 | 0.0% | Active |
Pick this model first.
Works — usually a fine pick.
Other models will serve you better.
Fit assertions set by the curator pipeline. 48 use cases mapped.
Model catalogue
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": "mistralai/mistral-large-3-675b-instruct-2512",
"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 X-Stav-App-Id: <uuid> to attribute requests to a registered app.