> ## Documentation Index
> Fetch the complete documentation index at: https://docs.opentype.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# not_configured

> HTTP 503 on /v1/runs routes: something the run needs is not configured on the service. Retry later; nothing in your request causes it.

`not_configured` means the service is missing a part it needs to handle runs. Read this page when a runs route answers with this code; it is a service-side problem.

| HTTP  | `code`           | Retryable                                                              |
| ----- | ---------------- | ---------------------------------------------------------------------- |
| `503` | `not_configured` | Later, with backoff. For `POST /v1/runs`, use a new `Idempotency-Key`. |

## What happened

Routes: `POST /v1/runs`, `GET /v1/runs`, `GET /v1/runs/{run_id}`, `GET /v1/runs/{run_id}/stream`.

Something a run needs is not configured: the data store, the service's model list, the component that chooses a model, the model service, or the connection for the model chosen for this run. This is how the runs routes spell it; other routes use the more specific [database\_not\_configured](/problems/database_not_configured) or [billing\_not\_configured](/problems/billing_not_configured).

On `POST /v1/runs` the refusal can come before or after the run is admitted. If it came after, the run is stored as `pending` and is never charged; a replay with the same `Idempotency-Key` returns `202` with that pending run.

## How to fix

* Retry after a few minutes with backoff. A fast loop gets the same answer.
* On `POST /v1/runs`, use a **new** `Idempotency-Key` for the retry.
* `GET` routes have no key; retry them as they are.
* If it persists, report the `request_id`.

## Example

```json theme={"system"}
{"error":{"code":"not_configured","message":"a required dependency is not configured","request_id":"req_7d3f0c1a9b2e4f6a8c0d1e2f3a4b5c6d"}}
```

Retrying a read with backoff and your own request id:

<CodeGroup>
  ```bash curl theme={"system"}
  for attempt in 1 2 3 4; do
    STATUS=$(curl -sS -o response.json -w '%{http_code}' "https://api.opentype.dev/v1/runs?limit=20" \
      -H "Authorization: Bearer $OPENTYPE_API_KEY" \
      -H "x-request-id: $(uuidgen)")
    case "$STATUS" in
      5??) sleep $((2 ** attempt)) ;;  # back off, then try again
      *) break ;;
    esac
  done
  cat response.json
  ```

  ```typescript TypeScript theme={"system"}
  async function getWithRetry(path: string, maxAttempts = 4) {
    for (let attempt = 1; ; attempt++) {
      const requestId = crypto.randomUUID();
      const res = await fetch(`https://api.opentype.dev${path}`, {
        headers: {
          Authorization: `Bearer ${process.env.OPENTYPE_API_KEY}`,
          "x-request-id": requestId, // log it; quote it if the problem persists
        },
      });
      if (res.ok) return res.json();

      const code = (await res.json().catch(() => null))?.error?.code ?? `HTTP ${res.status}`;
      console.error(`GET ${path} -> ${res.status} ${code} (${requestId})`);
      if (res.status < 500 || attempt >= maxAttempts) throw new Error(`${code} (${requestId})`);
      await new Promise((r) => setTimeout(r, 2 ** attempt * 1000));
    }
  }

  const data = await getWithRetry("/v1/runs?limit=20"); // needs runs_read
  ```

  ```python Python theme={"system"}
  import os
  import time
  import uuid

  import requests

  def get_with_retry(path: str, max_attempts: int = 4) -> dict:
      for attempt in range(1, max_attempts + 1):
          request_id = str(uuid.uuid4())
          resp = requests.get(
              f"https://api.opentype.dev{path}",
              headers={
                  "Authorization": f"Bearer {os.environ['OPENTYPE_API_KEY']}",
                  "x-request-id": request_id,  # log it; quote it if the problem persists
              },
              timeout=30,
          )
          if resp.ok:
              return resp.json()

          try:
              code = resp.json()["error"]["code"]
          except ValueError:
              code = f"HTTP {resp.status_code}"
          print(f"GET {path} -> {resp.status_code} {code} ({request_id})")
          if resp.status_code < 500 or attempt == max_attempts:
              raise RuntimeError(f"{code} ({request_id})")
          time.sleep(2 ** attempt)

  data = get_with_retry("/v1/runs?limit=20")  # needs runs_read
  ```
</CodeGroup>

## Related

* [Error handling](/guides/error-handling) - a status-to-action table and a retry helper for every error.
* [Idempotency](/guides/idempotency) - when to reuse an `Idempotency-Key` and when to send a new one.
* [Request ids](/reference/request-ids) - send your own `x-request-id` and quote it when you report a problem.
* [Problem codes](/problems) - every code, its status, and whether a retry can help.