GET

/v1/schemas/nvidia/chat/nvidia%2Fnemotron-3.5-lightning-30b-a3b

kind inputactivity chathash 3368ef8f…extracted Oct 8, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 1 $defs
propertytypedescriptionconstraints
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…
modelstringdefault: "nvidia/nemotron-3.5-lightning-3…
temperaturenumberThe sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.0 < n ≤ 1 · default: 1
top_pnumberThe top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not reco…0 < n ≤ 1 · default: 0.95
max_tokensintegerThe maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.1 ≤ n ≤ 32768 · default: 16384
reasoning_budgetintegerMaximum number of tokens the model is allowed to use for internal reasoning ("thinking") before it is forced to end the reasoning trace. Use `-1` to disable budget enforcement. This can also be provided via `chat_template_kwargs.reasoning_budget` for backwards…-1 ≤ n ≤ 32768 · default: 16384
seedintegerIf specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.0 ≤ n ≤ 18446744073709552000 · nullable
streambooleanIf 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: true
stopstring[] | stringA string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"nvidia/nemotron-3.5-lightning-30b-a3b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}