BerriAI/litellm · error · HTTPException

{key} is over max limit set in config - user_value={value};

Error message

{key} is over max limit set in config - user_value={value}; max_value={upperbound_value}

What it means

Error "{key} is over max limit set in config - user_value={value}; max_value={upperbound_value}" thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/management_endpoints/key_management_endpoints.py:823

    if litellm.upperbound_key_generate_params is None:
        return

    for elem in data:
        key, value = elem
        upperbound_value = getattr(litellm.upperbound_key_generate_params, key, None)
        if upperbound_value is not None:
            if value is None:
                if fill_defaults:
                    setattr(data, key, upperbound_value)
            else:
                if key in [
                    "max_budget",
                    "max_parallel_requests",
                    "tpm_limit",
                    "rpm_limit",
                ]:
                    if value > upperbound_value:
                        raise HTTPException(
                            status_code=400,
                            detail={
                                "error": f"{key} is over max limit set in config - user_value={value}; max_value={upperbound_value}"
                            },
                        )
                elif key in ["budget_duration", "duration"]:
                    upperbound_duration = duration_in_seconds(duration=upperbound_value)
                    if value == "-1":
                        user_duration = float("inf")
                    else:
                        user_duration = duration_in_seconds(duration=value)
                    if user_duration > upperbound_duration:
                        raise HTTPException(
                            status_code=400,
                            detail={
                                "error": f"{key} is over max limit set in config - user_value={value}; max_value={upperbound_value}"
                            },
                        )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Lower the value to at most the configured max_value.
2. Ask the proxy admin to raise the limit in the proxy config if a higher value is legitimate.

When it happens

Trigger: Thrown at litellm/proxy/management_endpoints/key_management_endpoints.py:823 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/3b24c117b3e1a5e4. Report an issue: GitHub.