Claude Opus 5

Capabilities

Anthropic Messages — drop in your slug

Stav speaks the Anthropic Messages API. Point the Anthropic SDK at base_url="https://api.stav.ai/v1" and your existing code keeps working — including cache_control markers and thinking mode, which pass through to Anthropic verbatim. Set STAV_API_KEY and the curl below works.

curl https://api.stav.ai/v1/messages \
  -H "Authorization: Bearer $STAV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Already using the OpenAI SDK? The same model is reachable at POST /v1/chat/completions — drop in the slug above as the model field and it works.

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.

Inference runs in US on anthropic. The model was created in US as well. Both training and inference fall under US compelled-disclosure regimes (CLOUD Act / FISA 702). Not appropriate for EU regulated-sector workloads without explicit legal sign-off.