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

Body

application/json

Set or clear the org-level llm_judge model default.

model_settings=null clears the override (back to the code role default). A non-null entry must reference a model in MODEL_REGISTRY (422 otherwise); since the catalog == registry, anything the UI dropdown offers passes. The ModelChainEntry shape also validates the config knobs at the boundary.

​
model_settings
ModelChainEntry · object

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