GET

/v1/schemas/groq/chat/openai%2Fv1%2Fresponses?kind=output

kind outputactivity chathash 7d20a33a…extracted Sep 20, 2026version currentsource upstream spec ↗

Response body

27 properties · 17 required · 18 $defs
propertytypedescriptionconstraints
id*stringA unique identifier for the response.
object*enumThe object type, which is always `response`.response
status*enumThe status of the response generation. One of `completed`, `failed`, `in_progress`, or `incomplete`.completed | failed | in_progress | incomplete
created_at*integerThe Unix timestamp (in seconds) of when the response was created.
output*ResponseOutputItem[]An array of content items generated by the model.
model*stringThe model used for the response.
tools*ResponseTool[]The tools that were available to the model.
tool_choice*enum | objectControls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call …
truncation*enumThe truncation strategy used.auto | disabled
metadata*objectMetadata attached to the response.
temperature*numberThe sampling temperature used.
top_p*numberThe nucleus sampling parameter used.
service_tier*enumThe service tier used for processing.auto | default | flex
error*objectAn error object if the response failed.
incomplete_details*objectDetails about why the response is incomplete.
parallel_tool_calls*booleanWhether the model can run tool calls in parallel.
store*booleanWhether the response was stored.
previous_response_idstringNot supported. Always null.
reasoningobjectConfiguration options for [models that support reasoning](https://console.groq.com/docs/reasoning).
max_output_tokensintegerThe maximum number of tokens configured for the response.
instructionsstringThe system instructions used for the response.
textobjectText format configuration used for the response.
userstringThe user identifier.
usageResponseUsageUsage statistics for the response request.
backgroundbooleanWhether the response was generated in the background.default: false
top_logprobsintegerThe number of top log probabilities returned.default: 0
max_tool_callsintegerThe maximum number of tool calls allowed.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"groq","endpointId":"openai/v1/responses","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}