---
title: "Retrieve Experiment"
method: GET
path: "/api/v2/experiments/{experiment_id}/"
tags: ["experiments"]
---

# Retrieve Experiment

`GET /api/v2/experiments/{experiment_id}/`

RUD: Retrieve, Update, Delete single experiment.

GET /evaluations/experiments/<id>/
PATCH /evaluations/experiments/<id>/   — edit the definition (dataset,
    workflow, evaluators, config). Blocked while a run is in flight
    so the in-flight run can trust its dispatched definition.
    Trigger execution via POST /runs/, not PATCH.
DELETE /evaluations/experiments/<id>/

## Path parameters

- `experiment_id` string, required

## Headers

- `Authorization` string, required

## Response `200`

- ExperimentV2 — Serializer for ExperimentV2 model. Field aliasing: - `evaluator_ids` (preferred) - accepts/returns evaluator UUIDs - `evaluator_slugs` (deprecated) - alias for backward compatibility - workflow `type="eval"` (preferred) - canonical evaluation step name - workflow `type="evaluator"` (deprecated) - accepted on input, normalized to `eval` Write-side normalization (evaluator_ids → evaluator_slugs, workflow type aliases) lives in `ExperimentV2WriteMixin` and is shared with the create + update serializers.
  - `id` string, required
  - `evaluator_ids` string, required
  - `project` string, nullable
  - `name` string
  - `description` string
  - `unique_organization_id` string, required
  - `workflow` unknown
  - `workflow_count` integer
  - `evaluator_slugs` string[] — List of evaluators to run for producing scores for comparison
  - `evaluator_workflow_ids` string[] — List of WorkflowVersion IDs (eval_only) defining evaluator pipelines. Mutually exclusive with evaluator_slugs.
  - `resource_ids` string[] — All resource IDs referenced (evaluators, prompts) for reverse lookup on deletion
  - `batch_size` integer
  - `concurrency` integer
  - `enable_tracing` boolean
  - `status` 'draft' | 'pending' | 'paused' | 'running' | 'waiting_for_annotations' | 'completed' | 'failed' — * `draft` - Draft * `pending` - Pending * `paused` - Paused * `running` - Running * `waiting_for_annotations` - Waiting For Annotations * `completed` - Completed * `failed` - Failed
  - `progress` number, double
  - `metadata` unknown
  - `is_starred` boolean
  - `created_at` string, date-time, required
  - `updated_at` string, date-time, required
  - `started_at` string, date-time, nullable
  - `completed_at` string, date-time, nullable
  - `organization` integer, required
  - `created_by` integer, nullable, required
  - `dataset` string, nullable
  - `task_tracker` string, nullable

---

[API](https://skmtc.net/keywordsai/apis/api-reference.md) · [All operations](https://skmtc.net/keywordsai/apis/api-reference/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/keywordsai/api-reference/versions/c26d550029f8/schema)