JSON mode

Forces the model to output valid JSON by setting response_format. Always instruct the model to produce JSON in your prompt.

Syntax

openai-api

{ response_format: { type: "json_object" } }

Example

openai-api

const response = await client.chat.completions.create({
  model: "gpt-4o",
  response_format: { type: "json_object" },
  messages: [{
    role: "user",
    content: "Return a JSON object with name and age for Alice, age 28"
  }]
});

const data = JSON.parse(response.choices[0].message.content);
// { name: "Alice", age: 28 }