---
title: "Retrieve an Evaluator"
method: GET
path: "/v2/evaluators/{id}"
tags: ["Evals"]
---

# Retrieve an Evaluator

`GET /v2/evaluators/{id}`

Retrieve a single evaluator by its unique identifier. Returns the evaluator exactly as stored, including its type-specific configuration — prompt and model for LLM evaluators, source code for Python and TypeScript evaluators, the JSON Schema for schema evaluators, and so on.

Use this when you already know the evaluator id (for example to refresh the state of a resource you manage declaratively). To discover evaluator ids, list them with `GET /v2/evaluators`.

This endpoint returns the stored record, which carries more detail than the representation `GET /v2/evaluators` returns: `display_name` rather than `key`, `model` as an object rather than a provider-qualified string, plus the `owner`, `domain_id`, `metadata`, `enabled` and `output_type` fields.

## Path parameters

- `id` string, required — Unique identifier of the evaluator, as returned in the `_id` field by `GET /v2/evaluators`.

## Response `200`

The evaluator. The response shape depends on the evaluator `type`.

- union
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean' | 'categorical' | 'number' | 'string' — The type of output expected from the evaluator
    - `type` 'llm_eval', required
    - `mode` 'single' | 'jury' | 'null', nullable
    - `repetitions` integer, nullable
    - `model` object
      - `id` string, required
      - `integration_id` string, nullable
      - `model_parameters` object
        - `temperature` number
        - `max_tokens` number
        - `top_k` number
        - `top_p` number
        - `frequency_penalty` number
        - `presence_penalty` number
        - `reasoning_effort` string
        - `budget_tokens` number
    - `jury` object, nullable
      - `judges` object[], required
        - `model` object, required
          - `id` string, required
          - `integration_id` string, nullable
          - `model_parameters` object
            - `temperature` number
            - `max_tokens` number
            - `top_k` number
            - `top_p` number
            - `frequency_penalty` number
            - `presence_penalty` number
            - `reasoning_effort` string
            - `budget_tokens` number
        - `retry` object
          - `count` integer
          - `on_codes` integer[]
        - `fallbacks` object[]
          - `model` object, required
            - `id` string, required
            - `integration_id` string, nullable
            - `model_parameters` object
              - …
      - `replacement_judges` object[]
        - `model` object, required
          - `id` string, required
          - `integration_id` string, nullable
          - `model_parameters` object
            - `temperature` number
            - `max_tokens` number
            - `top_k` number
            - `top_p` number
            - `frequency_penalty` number
            - `presence_penalty` number
            - `reasoning_effort` string
            - `budget_tokens` number
        - `retry` object
          - `count` integer
          - `on_codes` integer[]
        - `fallbacks` object[]
          - `model` object, required
            - `id` string, required
            - `integration_id` string, nullable
            - `model_parameters` object
              - …
      - `min_successful_judges` integer
      - `tie_value` 'Tie'
    - `prompt` string, required
    - `categories` string[], nullable
    - `categorical_labels` object[], nullable
      - `value` string, required
      - `description` string
    - `dataset_id` string, nullable
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean' | 'categorical' | 'number' | 'string', required
    - `type` 'function_eval', required
    - `function_params` union, required
      - object
        - `type` 'contains', required
        - `value` string, required
      - object
        - `type` 'contains_none', required
        - `keywords` string[], required
      - object
        - `type` 'contains_all', required
        - `keywords` string[], required
      - object
        - `type` 'contains_any', required
        - `keywords` string[], required
      - object
        - `type` 'contains_email', required
      - object
        - `type` 'contains_url', required
      - object
        - `type` 'contains_valid_link', required
      - object
        - `type` 'start_with', required
        - `value` string, required
      - object
        - `type` 'ends_with', required
        - `value` string, required
      - object
        - `type` 'exact_match', required
      - object
        - `type` 'length_less_than', required
        - `value` number, required
      - object
        - `type` 'length_between', required
        - `min` number, required
        - `max` number, required
      - object
        - `type` 'length_greater_than', required
        - `value` number, required
      - object
        - `type` 'one_line', required
      - object
        - `type` 'regex', required
        - `pattern` string, required
      - object
        - `type` 'is_valid_json', required
      - object
        - `type` 'moderations_openai', required
      - object
        - `type` 'moderations_google', required
      - object
        - `type` 'bert_score', required
      - object
        - `type` 'bleu_score', required
      - object
        - `type` 'rouge_n', required
      - object
        - `type` 'meteor_score', required
      - object
        - `type` 'cosine_similarity', required
      - object
        - `type` 'levenshtein_distance', required
      - object
        - `type` 'keywords_match', required
        - `keywords` string[], required
      - object
        - `type` 'most_repeated_words', required
      - object
        - `type` 'flesch_reading_ease', required
      - object
        - `type` 'gse_english_level', required
      - object
        - `type` 'words_count', required
      - object
        - `type` 'sentences_count', required
      - object
        - `type` 'lexical_repetition', required
      - object
        - `type` 'grammar_diversity', required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'number'
    - `type` 'ragas', required
    - `model` object, required
      - `id` string, required
      - `integration_id` string, nullable
    - `ragas_metric` 'context_precision' | 'context_recall' | 'context_entities_recall' | 'harmfulness' | 'maliciousness' | 'coherence' | 'correctness' | 'conciseness' | 'response_relevancy' | 'faithfulness' | 'summarization' | 'noise_sensitivity', required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean'
    - `type` 'json_schema', required
    - `schema` string, required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean' | 'categorical' | 'number' | 'string' — The type of output expected from the evaluator
    - `type` 'http_eval', required
    - `url` string, required
    - `method` 'GET' | 'POST', required
    - `headers` object, required
    - `payload` object, required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean' | 'number'
    - `code` string, required
    - `type` 'python_eval', required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean' | 'categorical' | 'number' | 'string' — The type of output expected from the evaluator
    - `code` string, required
    - `type` 'typescript_eval', required
  - object
    - `enabled` boolean
    - `metadata` object, required
      - `required_model_with_tools_support` boolean
      - `required_retrieval_context` boolean
      - `required_expected_output` boolean
      - `supported_on_input_type` boolean
      - `supported_on_output_type` boolean
      - `support_use_as_guardrail` boolean
    - `_id` string, required
    - `display_name` string, required
    - `description` string, required
    - `owner` string, required
    - `created` string
    - `updated` string
    - `created_by_id` string, nullable
    - `updated_by_id` string, nullable
    - `domain_id` string, required
    - `project_id` string — Unique identifier of the project owning this evaluator.
    - `guardrail_config` union
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'boolean', required
        - `value` boolean, required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'categorical', required
        - `values` string[], required
      - object
        - `enabled` boolean
        - `alert_on_failure` boolean
        - `type` 'number', required
        - `value` number, required
        - `operator` 'eq' | 'ne' | 'gt' | 'gte' | 'lt' | 'lte', required
    - `output_type` 'boolean'
    - `type` 'bedrock_eval', required
    - `guardrail_identifier` string, required
    - `guardrail_version` string
    - `guardrail_region` string
    - `integration_id` string, nullable

## Other responses

- `404` — No evaluator with this id exists in the authenticated workspace, or the request carries no workspace.

---

[API](https://skmtc.net/orq-ai/apis/orq-ai-api.md) · [All operations](https://skmtc.net/orq-ai/apis/orq-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/orq-ai/orq-ai-api/versions/41c02aedc7c0/schema)