GET

/v1/schemas/grok/chat/v1/complete?kind=output

kind outputactivity chathash b9b181a7…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
8fef3a30eaf49596c4dfe70d5f01b85fc4063b25b5873e93874479ef8087f379
{
  "fetchedAt": 1783328713,
  "extractorVersion": "1",
  "verifiedAt": null
}

Response body

5 properties · 4 required · 0 $defs
propertytypedescriptionconstraints
completion*stringThe completion content up to and excluding stop sequences.
id*stringID of the completion response.
model*stringThe model that handled the request.
type*stringCompletion response object type. This is always `"completion"`.
stop_reasonanyThe reason to stop completion. `"stop_sequence"` means the inference has reached a model-defined or user-supplied stop sequence in `stop`. `"length"` means the inference result has reached models' maximum allowed token length or user defined value in `max_toke…

Validate a payload

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