Structured outputs

Force responses into JSON or a JSON Schema with response_format.

Set response_format to {"type": "json_object"} for free-form JSON, or {"type": "json_schema", ...} to constrain output to a schema. Generation is grammar-constrained on the server, so the output always parses.

curl https://api.sara-ai.kz/v1/chat/completions \
  -H "Authorization: Bearer $SARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-31b",
    "messages": [{"role": "user", "content": "Give me a city and its country."}],
    "response_format": {"type": "json_schema", "json_schema": {
      "name": "city",
      "schema": {
        "type": "object",
        "properties": { "city": { "type": "string" }, "country": { "type": "string" } },
        "required": ["city", "country"],
        "additionalProperties": false
      }
    }}
  }'