ResponseFormat class sealed

Specifies the format that the model must output.

Compatible with GPT-4o, GPT-4o mini, GPT-4 Turbo, and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.

Example

// Request JSON output
final request = ChatCompletionCreateRequest(
  model: 'gpt-4o',
  messages: [...],
  responseFormat: ResponseFormat.jsonObject(),
);

// Request specific JSON schema
final request = ChatCompletionCreateRequest(
  model: 'gpt-4o',
  messages: [...],
  responseFormat: ResponseFormat.jsonSchema(
    name: 'person',
    schema: {
      'type': 'object',
      'properties': {
        'name': {'type': 'string'},
        'age': {'type': 'integer'},
      },
      'required': ['name', 'age'],
    },
  ),
);

Implementers

• JsonObjectResponseFormat
• JsonSchemaResponseFormat
• TextResponseFormat

Annotations

• @immutable

Constructors

ResponseFormat.fromJson(Map<String, dynamic> json)

Creates a ResponseFormat from JSON.

factory

Properties

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

type → String

The type identifier for this format.

no setter

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toJson() → Map<String, dynamic>

Converts to JSON.

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Static Methods

jsonObject() → ResponseFormat

Creates a JSON object response format.

jsonSchema({required String name, required Map<String, dynamic> schema, String? description, bool strict = true}) → ResponseFormat

Creates a JSON schema response format.

text() → ResponseFormat

Creates a text response format.