BerriAI/litellm · error · HTTPException

Not Found

Error message

Not Found

What it means

Error "Not Found" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/health_endpoints/_health_endpoints.py:1714

    from service) and blocks until the in-flight request counter drains to
    zero or ``GRACEFUL_SHUTDOWN_TIMEOUT`` elapses. Unlike a fixed ``sleep``,
    this returns as soon as real in-flight work is done.

    Wire it up as:

    ```yaml
    lifecycle:
      preStop:
        httpGet:
          path: /health/drain
          port: 4000
          httpHeaders:
            - name: X-Drain-Token
              value: <same value as drain_endpoint_token>
    ```
    """
    if not _drain_endpoint_enabled():
        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Not Found")
    _authorize_drain_request(request)
    GracefulShutdownManager.start_shutdown()
    drained: Final = await GracefulShutdownManager.wait_for_drain(exclude_self=True)
    return {"status": "drained", "drained_requests": drained}


@router.get(
    "/health/liveliness",  # Historical LiteLLM name; doesn't match k8s terminology but kept for backwards compatibility
    tags=["health"],
)
@router.get(
    "/health/liveness",  # Kubernetes has "liveness" probes (https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/#define-a-liveness-command)
    tags=["health"],
)
async def health_liveliness(response: Response):
    """
    Unprotected endpoint for checking if worker is alive.

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Verify the requested health endpoint path and resource identifier.
2. Check that the resource exists (e.g. correct model or key alias).

When it happens

Trigger: Thrown at litellm/proxy/health_endpoints/_health_endpoints.py:1714 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/f9a110f50cf2c92b. Report an issue: GitHub.