Skip to main content
Use text.format on POST /v1/responses to force the model’s output into JSON. It follows the OpenAI Responses text.format spec and is available only in backbone mode (mode:"model").
text.format requires mode:"model". On the default agent mode it returns 400 unsupported_parameter (param: "text") — free-text that explodes downstream is more expensive than an interface error. The Answers API (/v1/chat/completions) likewise rejects response_format with 400.

​
json_object

Constrains the output to a syntactically valid JSON object (no schema): 
{
  "model": "mirobody-flash",
  "mode": "model",
  "input": "Reply with a JSON object having keys a and b.",
  "text": { "format": { "type": "json_object" } }
}
The message text is a JSON string you parse yourself: 
{ "output_text": "{\"a\":1,\"b\":2}", "status": "completed", ... }

​
json_schema

Constrains the output to a schema you supply. Set strict: true for exact schema adherence: 
curl https://mirobody-api.thetahealth.ai/v1/responses \
  -H "Authorization: Bearer $MIROBODY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "mirobody-flash",
        "mode": "model",
        "input": "Give me a manifest for apples with count 3.",
        "text": {
          "format": {
            "type": "json_schema",
            "name": "manifest",
            "strict": true,
            "schema": {
              "type": "object",
              "properties": {
                "item":  { "type": "string" },
                "count": { "type": "integer" }
              },
              "required": ["item", "count"],
              "additionalProperties": false
            }
          }
        }
      }'

from openai import OpenAI

client = OpenAI(api_key="mb_live_...", base_url="https://mirobody-api.thetahealth.ai/v1")

resp = client.responses.create(
    model="mirobody-flash",
    extra_body={"mode": "model"},
    input="Give me a manifest for apples with count 3.",
    text={
        "format": {
            "type": "json_schema",
            "name": "manifest",
            "strict": True,
            "schema": {
                "type": "object",
                "properties": {"item": {"type": "string"}, "count": {"type": "integer"}},
                "required": ["item", "count"],
                "additionalProperties": False,
            },
        }
    },
)
print(resp.output_text)   # {"item":"apples","count":3}

​
Provider fallback

text.format passes through to the underlying model. When the backing provider has no native json_schema support, Mirobody automatically retries once as json_object with the schema injected into the system prompt. The retry is transparent — you still get schema-shaped JSON back — so treat structured output as reliable without knowing which provider backs a tier.

​
See also

  • Backbone mode — mode:"model", the prerequisite for text.format.
  • Function calling — for tool-argument shaping, pair text.format with tool_choice:"required".