API reference · Schema
EvaluationJudgeInput
modelstringrequiredModel ID (`publisher/name`)
1–256 characters
instructionsstringrequiredWhat the judge should assess, a template over the row (`{{column}}`). The texts being judged are added after it by the platform.
1–20000 characters
max_tokensintegerMost tokens per judge answer (default 512)
1–4096
temperaturenumberDefault 0
0–2
Example
{
"model": "qwen/qwen2.5-0.5b-instruct",
"instructions": "Classify the sentiment of the review: {{review}}",
"max_tokens": 1,
"temperature": 0
}