BerriAI/litellm · error · HTTPException
rpm limit higher than user max. User rpm limit={user_api_key
Error message
rpm limit higher than user max. User rpm limit={user_api_key_dict.rpm_limit}. User role={user_api_key_dict.user_role} What it means
Self-service team creation guard comparing the requested team limits against the calling key/user's own tpm/rpm allowance. Here the requested rpm_limit exceeds user_api_key_dict.rpm_limit, so a non-privileged caller is trying to mint a team with a higher rate budget than they themselves hold. Admins (or users without their own limits) are unaffected; the fix is to request a lower rpm_limit or have an admin create the team.
Source
Thrown at litellm/proxy/management_endpoints/team_endpoints.py:1092
# Validate team TPM/RPM against user's TPM/RPM limits
if (
data.tpm_limit is not None
and user_api_key_dict.tpm_limit is not None
and data.tpm_limit > user_api_key_dict.tpm_limit
):
raise HTTPException(
status_code=400,
detail={
"error": f"tpm limit higher than user max. User tpm limit={user_api_key_dict.tpm_limit}. User role={user_api_key_dict.user_role}"
},
)
if (
data.rpm_limit is not None
and user_api_key_dict.rpm_limit is not None
and data.rpm_limit > user_api_key_dict.rpm_limit
):
raise HTTPException(
status_code=400,
detail={
"error": f"rpm limit higher than user max. User rpm limit={user_api_key_dict.rpm_limit}. User role={user_api_key_dict.user_role}"
},
)
def _check_team_budget_update_authority(
data: UpdateTeamRequest,
user_api_key_dict: UserAPIKeyAuth,
existing_team_max_budget: float | None,
) -> None:
"""
Restrict who can grow a standalone team's spend ceiling on /team/update.
A team admin (already authorized via _verify_team_access) may keep or lower
the team budget, but only a proxy admin may grow it - by raising max_budget
above the team's current value or by removing the cap (setting it to None).View on GitHub (pinned to 77b7c6c40c)
Solutions
- Set rpm_limit at or below your user's rpm limit.
Defensive patterns
Strategy: validation
When it happens
Trigger: Thrown at litellm/proxy/management_endpoints/team_endpoints.py:1092 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/6c5ea2d90d3ef9ed.
Report an issue: GitHub.