Capabilities

Structured outputs

When you need a machine-readable answer rather than prose — extracting fields, classifying, building an API response — structured outputs make the model return valid JSON every time, so there's no fragile string-parsing on your end. Pendra enforces this with a grammar at generation time, not just a prompt instruction, so the output is guaranteed to parse.

JSON mode

Set response_format to { "type": "json_object" } and the reply is guaranteed to be syntactically valid JSON. Use this when you want JSON but don't need a specific shape — describe the fields you want in your prompt.

JSON Schema

For a guaranteed shape, pass { "type": "json_schema", "json_schema": { ... } }. The model is constrained to produce output matching your schema — the right keys, the right types — so you can deserialise straight into your own types.

If response_format is malformed — a type other than text, json_object, or json_schema, or { "type": "json_schema" } without its json_schema object — the request is rejected with a 422 before it runs, so a bad constraint fails fast instead of quietly returning unconstrained text.

from pendra import Pendra

client = Pendra()

response = client.chat.completions.create(
    model="qwen3.6:27b",
    messages=[{"role": "user", "content": "Extract the name and age from: Sara is 34."}],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "person",
            "schema": {
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "age": {"type": "integer"},
                },
            },
        },
    },
)
print(response.choices[0].message.content)  # {"name": "Sara", "age": 34}

import Pendra from 'pendra';

const client = new Pendra();

const response = await client.chat.completions.create({
  model: 'qwen3.6:27b',
  messages: [{ role: 'user', content: 'Extract the name and age from: Sara is 34.' }],
  response_format: {
    type: 'json_schema',
    json_schema: {
      name: 'person',
      schema: {
        type: 'object',
        properties: {
          name: { type: 'string' },
          age: { type: 'integer' },
        },
      },
    },
  },
});
console.log(response.choices[0].message.content); // {"name": "Sara", "age": 34}

Response

{ "name": "Sara", "age": 34 }

Structured outputs are a parameter of the chat endpoint. See the Chat completions API reference for the full field list.