Skip to main content
POST
Create evaluator version

Authorizations

X-API-Key
string
header
required

API key for authentication

Path Parameters

evaluator_uuid
string
required

Evaluator to add a version to

Example:

"f47ac10b-58cc-4372-a567-0e02b2c3d479"

Body

application/json

Request body for adding a version to an existing evaluator.

judge_model
string
required

The model that runs the judge, named the way its provider does, for example openai/gpt-4.1 or anthropic/claude-sonnet-4

system_prompt
string
required

Judge system prompt. May contain {{variable}} placeholders

output_config
OutputConfig · object | null

The scale points and their labels. Required for a rating evaluator. A binary evaluator uses the default Correct/Wrong labels unless you set your own

variables
VariableSpec · object[] | null

Declared prompt variables. Omit if the prompt has none. After the first version the variable names are fixed. You can change a variable's description or default, but not add, remove, or rename one

make_live
boolean
default:false

When true, immediately point the evaluator's live version at this new version

Response

Successful Response

version_uuid
string
required

ID of the newly created version

Required string length: 36
Example:

"6ba7b810-9dad-11d1-80b4-00c04fd430c8"

version_number
integer
required

The version's number. The first version is 1, and it goes up by one for each new version of the evaluator