BerriAI/litellm · error · ProxyException

Model {action} was saved to the database, but {missing_claus

Error message

Model {action} was saved to the database, but {missing_clause}{collateral_clause} Other pods reload on their own interval. Check server logs for 'Error upserting deployment' or 'Error creating deployment' for the cause.

What it means

Error "Model {action} was saved to the database, but {missing_clause}{collateral_clause} Other pods reload on their own interval. Check server logs for 'Error upserting deployment' or 'Error creating deployment' for the cause." thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/management_endpoints/model_management_endpoints.py:2407

        written_models=written_models,
        written_must_serve=True,
        still_desired=still_desired,
        live_after=live_after,
    )
    if not missing and not collateral:
        return
    missing_clause: Final = (
        f"the model id(s) {list(missing)} are not live in this pod's router after the reload and are not "
        "being served by this pod."
        if missing
        else "the reload it triggered degraded this pod's serving state."
    )
    collateral_clause: Final = (
        f" Previously served model id(s) {list(collateral)} are also no longer being served by this pod."
        if collateral
        else ""
    )
    raise ProxyException(
        message=(
            f"Model {action} was saved to the database, but {missing_clause}{collateral_clause} "
            "Other pods reload on their own interval. Check server logs for 'Error upserting deployment' or "
            "'Error creating deployment' for the cause."
        ),
        type=ProxyErrorTypes.internal_server_error,
        code=status.HTTP_500_INTERNAL_SERVER_ERROR,
        param=None,
    )


async def clear_cache() -> ReconcileOutcome:
    """
    Clear router caches and reload models.

    Returns what the reload saw (see ReconcileOutcome) so callers can pass it to
    raise_if_reload_degraded_serving.

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check server logs for 'Error upserting deployment' or 'Error creating deployment' for the cause.
2. Re-save the model after fixing the underlying error.

When it happens

Trigger: Thrown at litellm/proxy/management_endpoints/model_management_endpoints.py:2407 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/bab206593a876705. Report an issue: GitHub.