GET

/v1/schemas/nvidia/chat/z-ai/glm-5.3?kind=output

Accept:

kind outputactivity chathash bfdb66bc…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9f3518f0d3866da71d927164e77814959259e6219268e814a2d39ffcab0e5484` { "fetchedAt": 1791535404, "extractorVersion": "1", "verifiedAt": null }

Response body

6 properties · 3 required · 3 $defs

property	type	description	constraints
model*	string
choices*	ChatCompletionResponseChoice[]	The list of completion choices the model generated for the input prompt.
usage*	UsageInfo	Usage statistics for the completion request.
id	string	A unique identifier for the completion.
object	string		default: "chat.completion"
created	integer

Types

3 $defs

ChatCompletionResponseChoiceobject

index*	integer	The index of the choice in the list of choices (always 0).
message*	ChatMessage	A chat completion message generated by the model.
finish_reason	enum	The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished	stop \| length · nullable

ChatMessageobject

role*	string	The role of the message author.
content*	string	The contents of the message.

UsageInfoobject

prompt_tokens	integer	Number of tokens in the prompt.	default: 0
total_tokens	integer	Total number of tokens used in the request (prompt + completion).	default: 0
completion_tokens	integer	Number of tokens in the generated completion.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"z-ai/glm-5.3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}