GET

/v1/schemas/nvidia/chat/meta/muse-glimmer-30b?kind=output

Accept:

kind outputactivity chathash 48823596…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `75843643cce29874c4ea94739a57ea52ed8bce0a4ea9c98e4c2232acf636fe57` { "fetchedAt": 1791535404, "extractorVersion": "1", "verifiedAt": null }

Response body

3 properties · 3 required · 8 $defs

property	type	description	constraints
id*	string	A unique identifier for the completion.	format: uuid
choices*	Choice[]	The list of completion choices the model generated for the input prompt.
usage*	Usage	Usage statistics for the completion request.

Types

8 $defs

Choiceobject

index*	integer	The index of the choice in the list of choices (always 0).
message*	Message	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.	stop \| length \| tool_calls · nullable

ContentPartImageobject

image_url*	ImageURL
type*	enum		image_url

ContentPartTextobject

text*	string
type*	enum		text

FunctionCallobject

name*	string		nullable
arguments*	string		nullable

ImageURLobject

url*

string

Messageobject

role*	enum	The role of the message author.	system \| context \| user \| assistant \| tool
content	string \| ContentPartImage \| ContentPartText[]	The contents of the message. <br>To pass media (only with role=`user`): <br> - Use content parts. Text is passed with `type`=`text`. <br> - Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{fo…	nullable
tool_call_id	string	The id of the tool call.	nullable
tool_calls	ToolCall[]	The tool(s) called by the model.	nullable
reasoning_content	string	The model's chain-of-thought, returned on its own channel rather than mixed into `content` (non-OpenAI extension). Streamed as `delta.reasoning_content`.	nullable

ToolCallobject

id	string
type	enum	function · default: "function"
function*	FunctionCall

Usageobject

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

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"meta/muse-glimmer-30b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}