GET

/v1/schemas/grok/chat/v1%2Fchat%2Fcompletions?kind=output

kind outputactivity chathash de28c89cextracted Jul 6, 2026version currentsource upstream spec ↗

Response body

10 properties · 6 required · 12 $defs
propertytypedescriptionconstraints
choices*Choice[]A list of response choices from the model. The length corresponds to the `n` in request body (default to 1).
created*integerThe chat completion creation time in Unix timestamp.format: int64
id*stringA unique ID for the chat response.
model*stringModel ID used to create chat completion.
object*stringThe object type, which is always `"chat.completion"`.
service_tier*enumThe processing tier used for this request.default | priority
citationsanyList of all the external pages used by the model to answer.
output_filesanyFiles generated during the response (e.g., by the code execution tool). Only populated when `code_execution_files_output` is included.
system_fingerprintanySystem fingerprint, used to indicate xAI system configuration changes.
usageUsageToken usage information.nullable

Validate a payload

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