curl --request POST \
  --url https://api.arize.com/v2/evaluators/{evaluator_id}/versions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "commit_message": "Improve template wording",
  "template_config": {
    "name": "hallucination",
    "template": "Evaluate whether the output is factually grounded.\n\nInput: {input}\nOutput: {output}",
    "include_explanations": true,
    "use_function_calling_if_available": true,
    "classification_choices": {
      "hallucinated": 0,
      "factual": 1
    },
    "direction": "maximize",
    "data_granularity": "span",
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {
        "temperature": 0
      },
      "provider_parameters": {}
    }
  }
}
'

{
  "id": "RXZhbHVhdG9yVmVyc2lvbjoxMTpBYkNk",
  "evaluator_id": "RXZhbHVhdG9yOjEyOmFCY0Q=",
  "commit_hash": "b4c2d0e5f8a3b1629f7d4cc0328g98e2d5f921g3",
  "commit_message": "Improve template wording",
  "type": "template",
  "template_config": {
    "name": "hallucination",
    "template": "Evaluate whether the output is factually grounded...",
    "include_explanations": true,
    "use_function_calling_if_available": true,
    "classification_choices": {
      "hallucinated": 0,
      "factual": 1
    },
    "direction": "maximize",
    "data_granularity": "span",
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {
        "temperature": 0
      },
      "provider_parameters": {}
    }
  },
  "created_at": "2026-02-17T10:30:00.000Z",
  "created_by_user_id": "VXNlcjoxOm5OYkM="
}

Evaluators

Create evaluator version

Create a new version of an existing evaluator. The new version becomes the latest version immediately (versioning is append-only).

Payload Requirements

commit_message describes the changes in this version.
Provide either template_config or code_config to match the evaluator’s type. code_config.type is a separate inner discriminator (managed or custom) and is unrelated to the top-level type. Schema and constraints match Create Evaluator.

Valid example (template version)

{
  "commit_message": "Improve prompt template for better accuracy",
  "template_config": {
    "name": "hallucination",
    "template": "Given the input: {input}\nand output: {output}\nIs the output a hallucination? Explain your reasoning.",
    "include_explanations": true,
    "use_function_calling_if_available": true,
    "classification_choices": {"hallucinated": 0, "factual": 1},
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {"temperature": 0},
      "provider_parameters": {}
    }
  }
}

Invalid example (missing required commit_message)

{
  "template_config": {
    "name": "hallucination",
    "template": "Is this a hallucination?",
    "include_explanations": false,
    "use_function_calling_if_available": false,
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {},
      "provider_parameters": {}
    }
  }
}

This endpoint is in beta, read more here.

POST

evaluators

{evaluator_id}

versions

curl --request POST \
  --url https://api.arize.com/v2/evaluators/{evaluator_id}/versions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "commit_message": "Improve template wording",
  "template_config": {
    "name": "hallucination",
    "template": "Evaluate whether the output is factually grounded.\n\nInput: {input}\nOutput: {output}",
    "include_explanations": true,
    "use_function_calling_if_available": true,
    "classification_choices": {
      "hallucinated": 0,
      "factual": 1
    },
    "direction": "maximize",
    "data_granularity": "span",
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {
        "temperature": 0
      },
      "provider_parameters": {}
    }
  }
}
'

{
  "id": "RXZhbHVhdG9yVmVyc2lvbjoxMTpBYkNk",
  "evaluator_id": "RXZhbHVhdG9yOjEyOmFCY0Q=",
  "commit_hash": "b4c2d0e5f8a3b1629f7d4cc0328g98e2d5f921g3",
  "commit_message": "Improve template wording",
  "type": "template",
  "template_config": {
    "name": "hallucination",
    "template": "Evaluate whether the output is factually grounded...",
    "include_explanations": true,
    "use_function_calling_if_available": true,
    "classification_choices": {
      "hallucinated": 0,
      "factual": 1
    },
    "direction": "maximize",
    "data_granularity": "span",
    "llm_config": {
      "ai_integration_id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==",
      "model_name": "gpt-4o",
      "invocation_parameters": {
        "temperature": 0
      },
      "provider_parameters": {}
    }
  },
  "created_at": "2026-02-17T10:30:00.000Z",
  "created_by_user_id": "VXNlcjoxOm5OYkM="
}

Authorizations

Authorization

string

header

required

Most Arize AI endpoints require authentication. For those endpoints that require authentication, include your API key in the request header using the format

Path Parameters

evaluator_id

string

required

The unique evaluator identifier (base64) A universally unique identifier (base64-encoded opaque string).

Example:

"RW50aXR5OjEyMzQ1"

Body

application/json

Body containing evaluator version creation parameters

Option 1
Option 2

Payload for an evaluator version: exactly one of template_config or code_config. Used both when creating an evaluator (initial version) and when appending a version.

commit_message

string

required

Commit message describing the changes

template_config

object

required

The template configuration for this version

Show child attributes

Response

Returns the created evaluator version

Option 1
Option 2

A versioned snapshot of an evaluator's configuration. Exactly one of template_config or code_config is present. The type field discriminates the branch and matches the parent evaluator's type.

string

required

The unique identifier for this version

evaluator_id

string

required

The parent evaluator ID

commit_hash

string

required

A unique hash identifying this version

commit_message

string | null

required

A message describing the changes in this version

created_at

string<date-time>

required

When this version was created

created_by_user_id

string | null

required

The unique identifier for the user who created this version

type

enum<string>

required

Discriminator identifying this as a template evaluator version. Always template for this variant.

Available options:

template

template_config

object

required

The LLM template configuration for this version

Show child attributes

List evaluator versions Get evaluator version

⌘I