BerriAI/litellm · error · ValueError

No deployments available for selected model. Passed model={m

Error message

No deployments available for selected model. Passed model={model_group}. Deployments={deployment_dict}

What it means

Deployment-selection failure in the lowest-TPM/RPM v2 strategy: after filtering, no healthy deployment with available RPM/TPM capacity remains for the requested model_group; the model group and deployment map are included for diagnosis (all cooldown, over quota, or misconfigured rpm/tpm).

Source

Thrown at litellm/router_strategy/lowest_tpm_rpm_v2.py:622

                    if _deployment_rpm is None:
                        _deployment_rpm = _deployment.get("rpm", None)
                    if _deployment_rpm is None:
                        _deployment_rpm = _deployment.get("litellm_params", {}).get("rpm", None)
                    if _deployment_rpm is None:
                        _deployment_rpm = _deployment.get("model_info", {}).get("rpm", None)
                    if _deployment_rpm is None:
                        _deployment_rpm = float("inf")

                    ### GET CURRENT RPM ###
                    current_rpm = rpm_values[index] if rpm_values else 0

                    deployment_dict[id] = {
                        "current_tpm": current_tpm,
                        "tpm_limit": _deployment_tpm,
                        "current_rpm": current_rpm,
                        "rpm_limit": _deployment_rpm,
                    }
            raise ValueError(
                f"{RouterErrors.no_deployments_available.value}. Passed model={model_group}. Deployments={deployment_dict}"
            )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Check that deployments exist and are healthy for the model group; verify tpm/rpm limits are not excluding all deployments.

When it happens

Trigger: Thrown at litellm/router_strategy/lowest_tpm_rpm_v2.py:622 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/adf63e7546e122b4. Report an issue: GitHub.