JSON mode

JSON mode forces a model to emit syntactically valid JSON. It’s a feature of the OpenAI Chat Completions API, enabled by setting response_format to {"type": "json_object"}. Use JSON mode when you need parseable JSON but don’t need to enforce a specific schema. For most production use cases, prefer structured outputs. Structured outputs constrain successful, complete responses to a JSON schema you provide. Handle refusals, output limits, and transport errors before accepting the parsed result; schema constraints don’t guarantee that every request completes.

On Model APIs, Muse Spark Open accepts json_object but doesn’t constrain output to JSON. Ask for JSON in your prompt and validate the response in your application.

How it works

Set BASETEN_API_KEY to your Baseten API key and install the OpenAI SDK with pip install openai. JSON mode tells the server to constrain the output to valid JSON. You still describe the fields you want in the prompt; the server only enforces well-formedness, not shape. To generate a JSON object: Run the following script:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://inference.baseten.co/v1",
    api_key=os.environ["BASETEN_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4.1-Flash-1017",
    messages=[
        {"role": "system", "content": "You are a helpful assistant that responds only in JSON."},
        {"role": "user", "content": "List three planets with their distance from the sun in km. Respond as a JSON object with a 'planets' array."},
    ],
    response_format={"type": "json_object"},
)

choice = response.choices[0]
if choice.finish_reason != "stop" or choice.message.refusal:
    raise RuntimeError("Generation did not return a complete JSON object.")
print(choice.message.content)

{"planets":[{"name":"Mercury","distance_from_sun_km":57910000},{"name":"Venus","distance_from_sun_km":108200000},{"name":"Earth","distance_from_sun_km":149600000}]}

Ask for JSON in the prompt so the model produces a useful shape. The server constrains output to valid JSON but doesn’t infer the schema from the request.

JSON mode versus structured outputs

Feature	JSON mode	Structured outputs
Output guarantee	Valid JSON	Valid JSON that matches your schema
Schema enforcement	None	Schema-constrained generation on supporting models
Setup	Set `response_format` to `json_object`	Provide a JSON schema or Pydantic model
Best for	Lightweight extraction, ad hoc responses	Production data extraction, typed pipelines

Reach for JSON mode when you don’t want to define a schema and the downstream consumer can tolerate flexible field sets. Otherwise, use structured outputs.

Model support

JSON mode and structured outputs are supported on a per-model basis. See the feature support table on the Model APIs overview for which models support each.

Structured outputs: Schema-enforced JSON output.
Model APIs overview: Supported models and feature matrix.
Chat Completions reference: Full request and response schema.

Get started

Model APIs

Baseten Grid

Inference

Frontier Gateway

Training

Sandboxes

Development

Deployment

Engines

Model Labs

Organization

Hosting options

Observability

Troubleshooting

How it works

JSON mode versus structured outputs

Model support

​How it works

​JSON mode versus structured outputs

​Model support

​Related

How it works

JSON mode versus structured outputs

Model support

Related