---
title: "Create evaluator"
method: POST
path: "/v1/platform/evaluators"
tags: ["evaluators"]
---

# Create evaluator

`POST /v1/platform/evaluators`

Create a new LLM or code evaluator for the current workspace.

## Request body

- EvaluatorsCreateEvaluatorRequest
  - `code_evaluator` EvaluatorsCreateCodeEvaluatorRequest
    - `code` string
    - `language` string — Default: "python"
  - `llm_evaluator` EvaluatorsCreateLLMEvaluatorRequest
    - `commit_hash_or_tag` string
    - `prompt_repo_handle` string
    - `variable_mapping` object
  - `name` string
  - `type` 'llm' | 'code'

## Response `201`

Created

- EvaluatorsCreateEvaluatorResponse
  - `evaluator` EvaluatorsEvaluator
    - `code_evaluator` EvaluatorsCodeEvaluator
      - `code` string
      - `evaluator_id` string
      - `language` string — Default: "python"
    - `created_at` string
    - `created_by` string
    - `feedback_keys` string[]
    - `id` string
    - `llm_evaluator` EvaluatorsLLMEvaluator
      - `annotation_queue_id` string
      - `commit_hash_or_tag` string
      - `corrections_dataset_id` string
      - `evaluator_id` string
      - `num_few_shot_examples` integer
      - `prompt_id` string
      - `prompt_repo_handle` string
      - `use_corrections_dataset` boolean — Derived from the evaluator's run rules — shared across all rules on this evaluator. Nil when the evaluator has no run rules.
      - `variable_mapping` object — JSONB
    - `name` string
    - `run_rules` EvaluatorsEvaluatorRunRule[]
      - `corrections_dataset_id` string
      - `dataset_id` string
      - `dataset_name` string
      - `group_by` string
      - `id` string
      - `num_few_shot_examples` integer
      - `session_id` string
      - `session_name` string
      - `use_corrections_dataset` boolean
    - `spend_usd` number — Sum of LLM-as-judge run rule spend for the requested period (omitted when feature is disabled).
    - `tenant_id` string
    - `type` 'llm' | 'code'
    - `updated_at` string

## Other responses

- `400` — Bad Request
- `401` — Unauthorized
- `403` — Forbidden
- `500` — Internal Server Error

---

[API](https://skmtc.net/langchain-ai/apis/langsmith.md) · [All operations](https://skmtc.net/langchain-ai/apis/langsmith/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/langchain-ai/langsmith/revisions/a0acb3a6a101/schema)