Structured JSON output

Request structured JSON

Send response_format when the selected model route advertises structured_output in GET /v1/models. Kendr managed routing filters its candidates for that capability. An exact alias without the capability fails instead of silently dropping the schema.

curl https://api.kendr.org/v1/chat/completions \
  -H "Authorization: Bearer $KENDR_API_KEY" \
  -H "Idempotency-Key: structured-ticket-001" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kendr-intelligent",
    "messages": [{"role": "user", "content": "Classify: Checkout fails after payment."}],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "support_ticket",
        "strict": true,
        "schema": {
          "type": "object",
          "properties": {
            "category": {"type": "string"},
            "urgent": {"type": "boolean"}
          },
          "required": ["category", "urgent"],
          "additionalProperties": false
        }
      }
    }
  }'

Treat the returned assistant content as untrusted input until your application parses and validates it against the same schema. Compatibility support routes the request to a capable model; it does not replace application-side validation.

Validate before acting

Check for refusal and a non-success finish reason before parsing. A schema constrains shape, not factual correctness. Validate required fields, types, enums, and unexpected properties before storing a result.

import json

# response is returned by client.chat.completions.create(...).
choice = response.choices[0]
if choice.finish_reason != "stop" or getattr(choice.message, "refusal", None):
    raise ValueError("Response needs review")
value = json.loads(choice.message.content or "null")
if not isinstance(value, dict) or set(value) != {"category", "urgent"}:
    raise ValueError("Unexpected fields")
if not isinstance(value["category"], str) or type(value["urgent"]) is not bool:
    raise ValueError("Unexpected field types")