feat(router.py): add 'get_model_info' helper function to get the mode…

…l info for a specific model, based on it's id

litellm/router.py

@@ -2590,6 +2590,16 @@ def get_deployment(self, model_id: str):
                     return model
         return None
 
+    def get_model_info(self, id: str) -> Optional[dict]:
+        """
+        For a given model id, return the model info
+        """
+        for model in self.model_list:
+            if "model_info" in model and "id" in model["model_info"]:
+                if id == model["model_info"]["id"]:
+                    return model
+        return None
+
     def get_model_ids(self):
         ids = []
         for model in self.model_list:
@@ -2904,15 +2914,10 @@ def _common_checks_available_deployment(
                 m for m in self.model_list if m["litellm_params"]["model"] == model
             ]
 
-        verbose_router_logger.debug(
-            f"initial list of deployments: {healthy_deployments}"
-        )
+        litellm.print_verbose(f"initial list of deployments: {healthy_deployments}")
 
-        verbose_router_logger.debug(
-            f"healthy deployments: length {len(healthy_deployments)} {healthy_deployments}"
-        )
         if len(healthy_deployments) == 0:
-            raise ValueError(f"No healthy deployment available, passed model={model}")
+            raise ValueError(f"No healthy deployment available, passed model={model}. ")
         if litellm.model_alias_map and model in litellm.model_alias_map:
             model = litellm.model_alias_map[
                 model

litellm/router_strategy/lowest_tpm_rpm_v2.py

@@ -79,10 +79,12 @@ def pre_call_check(self, deployment: Dict) -> Optional[Dict]:
                     model=deployment.get("litellm_params", {}).get("model"),
                     response=httpx.Response(
                         status_code=429,
-                        content="{} rpm limit={}. current usage={}".format(
+                        content="{} rpm limit={}. current usage={}. id={}, model_group={}. Get the model info by calling 'router.get_model_info(id)".format(
                             RouterErrors.user_defined_ratelimit_error.value,
                             deployment_rpm,
                             local_result,
+                            model_id,
+                            deployment.get("model_name", ""),
                         ),
                         request=httpx.Request(method="tpm_rpm_limits", url="https://github.com/BerriAI/litellm"),  # type: ignore
                     ),