Request JSON output using response_format parameter
Use response_format.type set to 'json_schema' or 'json_object' to get structured API responses.
response_format.type = "json_schema"
response_format.json_schema = {
"type": "object",
"properties": {
"invoice_vendor": {"type": "string"},
"invoice_amount": {"type": "number"},
"invoice_date": {"type": "string", "format": "date"}
},
"required": ["invoice_vendor", "invoice_amount", "invoice_date"]
} json
This snippet shows how to configure the API to return a JSON object that adheres to a defined schema. The `response_format.type` can be set to `json_schema` to enforce a specific structure or `json_object` for any well-formed JSON. The `json_schema` field accepts a JSON Schema object to define the expected output structure.
Configure the API to return structured JSON output by setting the `response_format.type` parameter to `json_schema` or `json_object`. Provide a JSON schema to define the exact structure required for the model's response, ensuring type-safe and predictable data extraction.
This method leverages the API's capability to parse and generate data according to a predefined schema, ensuring that the output is not free-form text but a structured object that can be easily processed by downstream applications.
- Structured Outputs ↗xAI · xAI Docs: Guides · May 11, 2026 · paraphrased
First seen on Subvolts May 11, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Structured OutputsxAI · xAI Docs: Guides · May 11, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- HeuristicProvide conversation history for contextInclude previous prompts and results in new requests to maintain context. · 3 min
- HeuristicUse roles to provide context to the modelSpecify roles like system, user, and assistant to guide model behavior and conversation history. · 5 min
- Setting tipEnable streaming output for text generation modelsSet stream to true in your API request to get real-time text generation. · 1 min
- Setting tipManually override request timeout for reasoning models with streamingAdjust request timeout when streaming with reasoning models to prevent premature connection closure. · 5 min
- Code snippetUse tool calling for strictly conforming JSON argumentsxAI models generate tool call arguments that strictly conform to the tool's input JSON Schema. · 5 min
- HeuristicProvide Clear Instructions for Code ExecutionGive detailed instructions, specify data formats and constraints, and provide context for code execution. · 2 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with Grok.
- Where did this come from?
- xAI (xAI Docs: Guides). Subvolts collected, normalized and credited it; the link above opens the original.