Skip to main content
PUT
/
config
/
openai
{
  "updated": true,
  "config": {},
  "updated_at": {}
}

​
Overview

Updates OpenAI configuration settings for your organization, including model preferences, rate limits, and API parameters.

​
Request Body

​
default_model
string
Default model for evaluations (e.g., “gpt-4”, “gpt-3.5-turbo”)
​
max_tokens
integer
Maximum tokens per request
​
temperature
number
Temperature setting for model responses
​
rate_limits
object
Rate limiting configuration
​
fallback_models
array
Alternative models to use if primary model fails

​
Response

​
updated
boolean
required
Whether configuration was successfully updated
​
config
object
required
Updated configuration settings
​
updated_at
datetime
required
Configuration update timestamp

​
Examples

curl -X PUT https://api.judge.example.com/config/openai \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "default_model": "gpt-4",
    "max_tokens": 4096,
    "temperature": 0.2,
    "rate_limits": {
      "requests_per_minute": 100,
      "tokens_per_minute": 200000
    }
  }'