Skip to main content
GET
/
v1
/
policies
/
judge-model
Get the org-level llm_judge model default
curl --request GET \
  --url https://api-sandbox.featherhq.com/v1/policies/judge-model \
  --header 'x-api-key: <api-key>'
{
  "model_settings": {
    "model": "<string>",
    "config": {
      "temperature": 123,
      "max_tokens": 123,
      "top_p": 123,
      "stop_sequences": [
        "<string>"
      ],
      "request_timeout_ms": 123,
      "thinking_budget": 2
    }
  }
}

Authorizations

​
x-api-key
string
header
required

Response

Successful Response

The org-level default model for llm_judge policy checks.

model_settings is the org's chosen ModelChainEntry ({model, config}), or null when unset — in which case the runtime falls back to the code role default (gpt-5.4-mini / effort low). The UI renders that fallback label from the model catalog's policy_judge role default, so this response carries ONLY the override.

​
model_settings
ModelChainEntry · object