Structured Outputs

Structured Outputs ensure the model generates responses that match your supplied JSON Schema. This is essential for applications that need to parse model output programmatically.

Two approaches

Mode	`response_format.type`	Description
JSON Schema (recommended)	`json_schema`	Model strictly follows your schema definition
JSON Object (legacy)	`json_object`	Model outputs valid JSON but without schema enforcement

Example: Extract structured data

from openai import OpenAI
import json

client = OpenAI(
    base_url="https://api-inference.bitdeer.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[
        {
            "role": "system",
            "content": "You are a data extraction assistant. Extract expense information from the user's input.",
        },
        {
            "role": "user",
            "content": "I spent $120 on dinner last Friday and bought office supplies for $45 on Monday.",
        },
    ],
    max_tokens=1024,
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "expense_report",
            "schema": {
                "type": "object",
                "properties": {
                    "expenses": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "description": {"type": "string"},
                                "amount": {"type": "number"},
                                "date": {"type": "string"},
                                "category": {"type": "string"},
                            },
                            "required": ["description", "amount"],
                        },
                    },
                    "total": {"type": "number"},
                },
                "required": ["expenses", "total"],
            },
            "strict": True,
        },
    },
)

result = json.loads(response.choices[0].message.content)
print(json.dumps(result, indent=2))

Expected output

{
  "expenses": [
    {"description": "Dinner", "amount": 120, "date": "last Friday", "category": "Food"},
    {"description": "Office supplies", "amount": 45, "date": "Monday", "category": "Office"}
  ],
  "total": 165
}

Schema requirements

When strict: true:

Supported types: string, number, integer, boolean, array, object, enum, anyOf
All object properties must be explicitly listed
Unsupported schemas will return an error

JSON Object mode (simpler alternative)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    messages=[{"role": "user", "content": "List 3 colors as JSON."}],
    max_tokens=256,
    response_format={"type": "json_object"},
)

This guarantees valid JSON output but does not enforce a specific structure.

Two approaches

Example: Extract structured data

Expected output

Schema requirements

JSON Object mode (simpler alternative)

On this page