GET

/v1/schemas/nvidia/chat/nvidia/llama-3.1-nemotron-safety-guard-8b-v3

Accept:

kind inputactivity chathash f4f1c395…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `bdaa63756ada4e7f91811ae6981fa0e77f9a4cc353d43f58dfd3cd0c7045b0c0` { "fetchedAt": 1791535404, "extractorVersion": "1", "verifiedAt": null }

Request body

4 properties · 1 required · 1 $defs

property	type	description	constraints
messages*	Message[]	A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first me…
model	string		default: "nvidia/llama-3.1-nemotron-safet…
temperature	number	The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be.	0 ≤ n ≤ 1 · default: 0
stream	boolean	If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.	default: false

Types

1 $defs

Messageobject

role*	enum	The role of the message author.	system \| context \| user \| assistant
content*	string	The contents of the message.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}