GET

/v1/schemas/nvidia/chat/meta%2Fllama2-70b?kind=output

kind outputactivity chathash b35389e1…extracted Oct 9, 2026version currentsource upstream spec ↗

Response body

6 properties · 3 required · 3 $defs
propertytypedescriptionconstraints
model*string
choices*ChatCompletionResponseChoice[]The list of completion choices the model generated for the input prompt.
usage*UsageInfoUsage statistics for the completion request.
idstringA unique identifier for the completion.
objectstringdefault: "chat.completion"
createdinteger

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"meta/llama2-70b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}