diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py
index 999191a8c..fc8732dfd 100644
--- a/litellm/integrations/prometheus.py
+++ b/litellm/integrations/prometheus.py
@@ -12,7 +12,7 @@ import litellm, uuid
 from litellm._logging import print_verbose, verbose_logger
 
 
-class prometheusLogger:
+class PrometheusLogger:
     # Class variables or attributes
     def __init__(
         self,
@@ -42,7 +42,7 @@ class prometheusLogger:
                 labelnames=["user", "key", "model"],
             )
         except Exception as e:
-            print_verbose(f"Got exception on init s3 client {str(e)}")
+            print_verbose(f"Got exception on init prometheus client {str(e)}")
             raise e
 
     async def _async_log_event(
@@ -65,7 +65,7 @@ class prometheusLogger:
             litellm_params = kwargs.get("litellm_params", {}) or {}
             proxy_server_request = litellm_params.get("proxy_server_request") or {}
             end_user_id = proxy_server_request.get("body", {}).get("user", None)
-            user_api_key = litellm_params.get("metadata", {}).get("api_key", None)
+            user_api_key = litellm_params.get("metadata", {}).get("user_api_key", None)
             tokens_used = response_obj.get("usage", {}).get("total_tokens", 0)
 
             print_verbose(
diff --git a/litellm/utils.py b/litellm/utils.py
index 5f11eb989..bcef061d6 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -66,6 +66,7 @@ from .integrations.weights_biases import WeightsBiasesLogger
 from .integrations.custom_logger import CustomLogger
 from .integrations.langfuse import LangFuseLogger
 from .integrations.datadog import DataDogLogger
+from .integrations.prometheus import PrometheusLogger
 from .integrations.dynamodb import DyanmoDBLogger
 from .integrations.s3 import S3Logger
 from .integrations.clickhouse import ClickhouseLogger
@@ -123,6 +124,7 @@ weightsBiasesLogger = None
 customLogger = None
 langFuseLogger = None
 dataDogLogger = None
+prometheusLogger = None
 dynamoLogger = None
 s3Logger = None
 genericAPILogger = None
@@ -1502,6 +1504,35 @@ class Logging:
                             user_id=kwargs.get("user", None),
                             print_verbose=print_verbose,
                         )
+                    if callback == "prometheus":
+                        global prometheusLogger
+                        verbose_logger.debug("reaches prometheus for success logging!")
+                        kwargs = {}
+                        for k, v in self.model_call_details.items():
+                            if (
+                                k != "original_response"
+                            ):  # copy.deepcopy raises errors as this could be a coroutine
+                                kwargs[k] = v
+                        # this only logs streaming once, complete_streaming_response exists i.e when stream ends
+                        if self.stream:
+                            verbose_logger.debug(
+                                f"prometheus: is complete_streaming_response in kwargs: {kwargs.get('complete_streaming_response', None)}"
+                            )
+                            if complete_streaming_response is None:
+                                continue
+                            else:
+                                print_verbose(
+                                    "reaches prometheus for streaming logging!"
+                                )
+                                result = kwargs["complete_streaming_response"]
+                        prometheusLogger.log_event(
+                            kwargs=kwargs,
+                            response_obj=result,
+                            start_time=start_time,
+                            end_time=end_time,
+                            user_id=kwargs.get("user", None),
+                            print_verbose=print_verbose,
+                        )
                     if callback == "generic":
                         global genericAPILogger
                         verbose_logger.debug("reaches langfuse for success logging!")
@@ -6111,7 +6142,7 @@ def validate_environment(model: Optional[str] = None) -> dict:
 
 
 def set_callbacks(callback_list, function_id=None):
-    global sentry_sdk_instance, capture_exception, add_breadcrumb, posthog, slack_app, alerts_channel, traceloopLogger, athinaLogger, heliconeLogger, aispendLogger, berrispendLogger, supabaseClient, liteDebuggerClient, llmonitorLogger, promptLayerLogger, langFuseLogger, customLogger, weightsBiasesLogger, langsmithLogger, dynamoLogger, s3Logger, dataDogLogger
+    global sentry_sdk_instance, capture_exception, add_breadcrumb, posthog, slack_app, alerts_channel, traceloopLogger, athinaLogger, heliconeLogger, aispendLogger, berrispendLogger, supabaseClient, liteDebuggerClient, llmonitorLogger, promptLayerLogger, langFuseLogger, customLogger, weightsBiasesLogger, langsmithLogger, dynamoLogger, s3Logger, dataDogLogger, prometheusLogger
     try:
         for callback in callback_list:
             print_verbose(f"callback: {callback}")
@@ -6179,6 +6210,8 @@ def set_callbacks(callback_list, function_id=None):
                 langFuseLogger = LangFuseLogger()
             elif callback == "datadog":
                 dataDogLogger = DataDogLogger()
+            elif callback == "prometheus":
+                prometheusLogger = PrometheusLogger()
             elif callback == "dynamodb":
                 dynamoLogger = DyanmoDBLogger()
             elif callback == "s3":