Force LLM responses into valid JSON format. Supports json_object (free-form JSON) and json_schema (schema-validated JSON).
Basic JSON Mode
const agent = new Agent({
name: 'Data Extractor',
instructions: 'Extract structured data from text.',
model: openai('gpt-4o'),
modelConfig: {
responseFormat: { type: 'json_object' }
}
});
Schema-Validated JSON
Force the response to match a specific schema:
const agent = new Agent({
name: 'Profile Extractor',
instructions: 'Extract person profile from text.',
model: openai('gpt-4o'),
modelConfig: {
responseFormat: {
type: 'json_schema',
json_schema: {
type: 'object',
properties: {
name: { type: 'string' },
age: { type: 'integer' },
email: { type: 'string' },
},
required: ['name', 'age', 'email'],
additionalProperties: false,
}
}
}
});
const result = await agent.process({ message: 'John Smith, 34, john@example.com' });
const profile = JSON.parse(result.message);
// { name: 'John Smith', age: 34, email: 'john@example.com' }
Provider Support
| Provider | json_object | json_schema | How |
|---|
| OpenAI | Native | Native | response_format API parameter |
| Gemini | Native | Native | responseMimeType + responseSchema |
| Anthropic | Not supported | Native (Claude 4.5+) | output_config.format |
| Bedrock | Not supported | Native (Claude 4.5+) | output_config in payload |
| Groq | Native | Not supported | response_format (OpenAI-compatible) |
| xAI | Native | Native | response_format (OpenAI-compatible) |
When json_object is not natively supported (Anthropic, Bedrock), add JSON instructions to your system prompt for best results.
With LLM Standalone
const extractor = LLM.openai('gpt-4o', {
responseFormat: { type: 'json_object' }
});
const result = await extractor.generate('List 3 colors with hex codes', {
system: 'Respond with valid JSON only.'
});
const data = JSON.parse(result.text);
Next Steps
Reasoning
Enable chain-of-thought thinking
Server-Side Tools
Provider-native web search and code execution
