---
title: "Run Eval"
method: POST
path: "/eval_configs/{id}/runs"
---

# Run Eval

`POST /eval_configs/{id}/runs`

## Request

- Base URL: `https://api.vogent.ai/api`
- URL: `https://api.vogent.ai/api/eval_configs/{id}/runs`
- Auth: HTTP bearer

Starts a new evaluation run for an AI evaluation configuration. Optionally specify specific record IDs to evaluate.

## Path parameters

- `id` string, required

## Request body

- RunEvalInput
  - `versionedPromptId` string, required: The ID of the versioned prompt to use for this eval run.
  - `callAgentId` string, required: The ID of the call agent to evaluate.
  - `evalRecordIds` string[]: Optional list of specific eval record IDs to run. If omitted, all records in the config are evaluated.

## Response `200`

Successful operation

- AIEvalRun
  - `id` string, required
  - `status` 'PENDING' | 'RUNNING' | 'SUCCESS' | 'FAILED' | 'CANCELLED', required: The status of an evaluation run.
  - `callAgentId` string, required
  - `versionedPromptId` string, required
  - `createdAt` string, date-time, required
  - `aggregateResult` AIEvalAggregateResult, required
    - `numFailing` integer, required
    - `numPassing` integer, required

## Other responses

- `400`: Invalid input
- `422`: Validation exception

---

[API](https://skmtc.dev/vogent/apis/vogent-openapi-3-0.md) - [All operations](https://skmtc.dev/vogent/apis/vogent-openapi-3-0/llms.txt) - [OpenAPI document](https://skmtc.dev/vogent/apis/vogent-openapi-3-0/revisions/a5966cc364ef?raw)