GET

/v1/schemas/moonshot/chat/v1%2Fresponses?kind=output

kind outputactivity chathash e41fa071…extracted Sep 19, 2026version currentsource upstream spec ↗

Response body

26 properties · 0 required · 13 $defs
propertytypedescriptionconstraints
idstringUnique identifier of the response.
objectenumresponse
created_atintegerUnix timestamp of when the response was created.
completed_atanyUnix timestamp of when the response finished. Present when `status` is `completed` or `incomplete`; `null` when `status` is `in_progress` or `failed`.
statusenumResponse status. The opening snapshot of a stream is `in_progress`.in_progress | completed | incomplete | failed
modelstringModel that produced the response.
outputResponsesOutputItem[]The output item array, ordered as web_search_call (if any), reasoning, message, tool calls.
usageResponsesUsageToken usage for this response.nullable
incomplete_detailsobjectReason the response is `incomplete`.
errorobjectError information when `status` is `failed`.
instructionsany
reasoningany
textany
toolsany
tool_choiceenumControls tool-calling behavior. With `auto`, the model decides whether to call a tool.auto · nullable
max_output_tokensany
temperatureany
top_pany
metadataany
parallel_tool_callsboolean
service_tierany
storebooleanAlways `false`.
backgroundanyAlways `false`.
previous_response_idanyAlways `null`.
conversationanyAlways `null`.
prompt_cache_optionsobjectThe context cache write options actually applied by the server. When the request omits prompt_cache_options, refer to the mode and ttl returned here

Validate a payload

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