GET

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

kind outputactivity chathash d344be58…extracted Sep 3, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
c2cb407652af94851e654028edb7ccef4ca55d38c384ab649f1984293022ae71
{
  "fetchedAt": 1788412236,
  "extractorVersion": "1",
  "verifiedAt": null
}

Response body

8 properties · 6 required · 2 $defs
propertytypedescriptionconstraints
content*MessageResponseContent[]Response message content.
id*stringUnique object identifier.
model*stringModel name that handled the request.
role*stringRole of the generated message. Always `"assistant"`
type*stringObject type. This is always `"message"` for message types.
usage*MessageUsageToken usage information.
stop_reasonanyReason to stop. `"stop_sequence"` means the inference has reached a model-defined or user-supplied stop sequence in `stop`. `"max_tokens"` means the inference result has reached models' maximum allowed token length or user defined value in `max_tokens`. `"end_…
stop_sequenceanyCustom stop sequence used to stop the generation.

Types

2 $defs

MessageResponseContentobject | object | object | …

MessageUsageobject

cache_creation_input_tokens*integer(Unsupported) Number of tokens written to the cache when creating a new entry.format: int32
cache_read_input_tokens*integerNumber of tokens retrieved from the cache for this request.format: int32
input_tokens*integerNumber of input tokens not served from cache (Anthropic semantics).format: int32
output_tokens*integerNumber of output tokens usedformat: int32

Validate a payload

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