Chat completions

POST /v1/chat/completions — same request and response shape as the OpenAI /v1/chat/completions endpoint. Standard fields (model, messages, temperature, max_tokens, stop, etc.) work as they do against OpenAI.

curl -sS https://api.alt.advania.ai/v1/chat/completions \
  -H "Authorization: Bearer $ALT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "advania-chat-small",
    "messages": [{"role": "user", "content": "Say hello in Swedish."}]
  }'

Model ids come from GET /v1/models — see Model catalog.

The full request/response shape is in the interactive OpenAPI.