BerriAI/litellm · error · HTTPException

Date range too large; maximum is {_SPEND_REPORT_MAX_RANGE_DA

Error message

Date range too large; maximum is {_SPEND_REPORT_MAX_RANGE_DAYS} days

What it means

Error "Date range too large; maximum is {_SPEND_REPORT_MAX_RANGE_DAYS} days" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/spend_tracking/spend_management_endpoints.py:1588

        )
    try:
        parsed = (
            datetime.strptime(start_date, "%Y-%m-%d").replace(tzinfo=timezone.utc),
            datetime.strptime(end_date, "%Y-%m-%d").replace(tzinfo=timezone.utc),
        )
    except ValueError:
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail="start_date and end_date must be in YYYY-MM-DD format",
        )
    start_date_obj, end_date_obj = parsed
    if end_date_obj < start_date_obj:
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail="start_date must be on or before end_date",
        )
    if end_date_obj - start_date_obj > timedelta(days=_SPEND_REPORT_MAX_RANGE_DAYS):
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail=f"Date range too large; maximum is {_SPEND_REPORT_MAX_RANGE_DAYS} days",
        )
    return parsed


def _resolve_spend_report_scope(
    user_api_key_dict: UserAPIKeyAuth,
    requested: str | None,
    caller_value: str | None,
    scope_name: str,
) -> str:
    """Return the scope value the caller may query spend for.

    Non-admin callers are clamped to their own identity: a ``requested`` value
    that differs from ``caller_value`` is a 403. Proxy admins (and admin
    viewers) may request any scope.
    """

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Shorten the requested date range to within the maximum allowed days; split large reports into multiple calls.

When it happens

Trigger: Thrown at litellm/proxy/spend_tracking/spend_management_endpoints.py:1588 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/ca268a3dcd8e92a8. Report an issue: GitHub.