Structured outputs

Structured outputs guarantee that the model response conforms to a JSON schema you define. Use this for typed API responses, database records, configuration objects or any case where free text is not acceptable.

JSON mode

Set response_format: {type: "json_object"} to receive valid JSON.

curl -X POST https://api.radium.cloud/v1/chat/completions \\
  -H "Authorization: Bearer $RADIUM_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "clarke-1.0",
    "messages": [{"role": "user", "content": "List two planets"}],
    "response_format": {"type": "json_object"}
  }'

from openai import OpenAI
client = OpenAI(api_key="YOUR_RADIUM_API_KEY", base_url="https://api.radium.cloud/v1")
response = client.chat.completions.create(
    model="clarke-1.0",
    messages=[{"role": "user", "content": "List two planets"}],
    response_format={"type": "json_object"},
)
print(response.choices[0].message.content)

import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.RADIUM_API_KEY, baseURL: "https://api.radium.cloud/v1" });
const response = await client.chat.completions.create({
  model: "clarke-1.0",
  messages: [{ role: "user", content: "List two planets" }],
  response_format: { type: "json_object" },
});
console.log(response.choices[0].message.content);

JSON schema

For stricter validation, supply a JSON schema using json_schema mode:

from openai import OpenAI
client = OpenAI(api_key="YOUR_RADIUM_API_KEY", base_url="https://api.radium.cloud/v1")

response = client.chat.completions.create(
    model="clarke-1.0",
    messages=[{"role": "user", "content": "List two planets with their diameters"}],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "planets",
            "schema": {
                "type": "object",
                "properties": {
                    "planets": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "name": {"type": "string"},
                                "diameter_km": {"type": "number"}
                            },
                            "required": ["name", "diameter_km"]
                        }
                    }
                },
                "required": ["planets"]
            }
        }
    },
)
print(response.choices[0].message.content)

Anthropic format

Structured outputs work in the Messages API using the same response_format parameter.

Limitations

Complex nested schemas with recursive references or union types may not be fully supported. Test your schema on a representative sample before deploying to production.