GET

/v1/schemas/nvidia/chat/nvidia%2Fising-calibration-1.5-31b

kind inputactivity chathash de5a78c7…extracted Oct 9, 2026version currentsource upstream spec ↗

Request body

8 properties · 2 required · 5 $defs
propertytypedescriptionconstraints
messages*NIMLLMChatCompletionMessage[]A list of messages comprising the conversation so far.items ≥ 1
model*stringThe model to use.default: "nvidia/ising-calibration-1.5-31…
max_tokensintegerThe maximum number of tokens that can be generated.1 ≤ n ≤ 32768 · nullable
seedintegerChanging the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant.-9223372036854776000 ≤ n ≤ 9223372036854776000 · nullable
streambooleanIf set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`nullable
temperaturenumberWhat sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.0 ≤ n ≤ 1 · nullable
top_pnumberAn alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.0 < n ≤ 1 · nullable
top_kintegerThe number of highest probability vocabulary tokens to keep for top-k sampling.n ≥ 1 · nullable

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"nvidia/ising-calibration-1.5-31b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}