diff --git a/litellm/router.py b/litellm/router.py index 46625b3c65..8ea1a124a4 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -1450,7 +1450,9 @@ class Router: raise original_exception ### RETRY #### check if it should retry + back-off if required - if "No models available" in str(e): + if "No models available" in str( + e + ) or RouterErrors.no_deployments_available.value in str(e): timeout = litellm._calculate_retry_after( remaining_retries=num_retries, max_retries=num_retries, @@ -2948,6 +2950,11 @@ class Router: model=model, healthy_deployments=healthy_deployments, messages=messages ) + if len(healthy_deployments) == 0: + raise ValueError( + f"{RouterErrors.no_deployments_available.value}, passed model={model}" + ) + if ( self.routing_strategy == "usage-based-routing-v2" and self.lowesttpm_logger_v2 is not None