> For the complete documentation index, see [llms.txt](/llms.txt).
> A full single-fetch corpus is available at [llms-full.txt](/llms-full.txt).
---
title: "Get run output"
description: "Fetch the final output of a completed run with a service key. A run that hasn't finished returns 409, so poll or follow its events first."
method: "GET"
endpoint: "/v1/runs/:runId/output"
order: 12
group: "Gateway: follow a run"
last_verified: 2026-10-08
---



`GET /v1/runs/:runId/output`

Fetch the final output of a completed run.


  ## Parameters

  - `X-API-KEY` _header_ **required** — A service key.
  - `runId` _string_ **required** — The run ID.



> A run that has not finished returns `409` with `run has not reached a terminal output state`. Poll until it completes, or follow its events and read the output after the terminal event.



  ## Request example


```bash
curl "https://gw.agnt5.com/v1/runs/{run_id}/output" \
  -H "X-API-KEY: {service_key}"
```

```javascript
fetch('https://gw.agnt5.com/v1/runs/' + runId + '/output', {
  headers: { 'X-API-KEY': serviceKey }
})
```


  ```json {{ title: 'Response' }}
  {
    "run_id": "7f6e5d4c-...",
    "status": "completed",
    "output": "Follow-up sent.",
    "output_ref": null,
    "source": "inline"
  }
  ```