diff --git a/litellm/__init__.py b/litellm/__init__.py
index 13e9f3dd3..cc6f88c0c 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -276,7 +276,7 @@ provider_list: List = [
     "vllm",
     "nlp_cloud",
     "bedrock",
-    "petals,"
+    "petals",
     "custom", # custom apis
 ]
 
diff --git a/litellm/llms/petals.py b/litellm/llms/petals.py
index e056d2049..648834540 100644
--- a/litellm/llms/petals.py
+++ b/litellm/llms/petals.py
@@ -32,8 +32,6 @@ def completion(
 
     model = model
 
-    # You could also use "meta-llama/Llama-2-70b-chat-hf" or any other supported model from 🤗 Model Hub
-
     tokenizer = AutoTokenizer.from_pretrained(model, use_fast=False, add_bos_token=False)
     model = AutoDistributedModelForCausalLM.from_pretrained(model)
     model = model.cuda()
@@ -76,6 +74,8 @@ def completion(
     print_verbose(f"raw model_response: {outputs}")
     ## RESPONSE OBJECT
     output_text = tokenizer.decode(outputs[0])
+    print("output text")
+    print(output_text)
     model_response["choices"][0]["message"]["content"] = output_text
 
     ## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here. 
diff --git a/litellm/main.py b/litellm/main.py
index eb209db7e..28292a6c4 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -959,8 +959,9 @@ def completion(
             or custom_llm_provider == "petals-team"
             or model in litellm.petals_models
         ):
-            custom_llm_provider = "baseten"
-
+            custom_llm_provider = "petals"
+            print("model on petals")
+            print(model)
             model_response = petals.completion(
                 model=model,
                 messages=messages,
@@ -970,7 +971,6 @@ def completion(
                 litellm_params=litellm_params,
                 logger_fn=logger_fn,
                 encoding=encoding, 
-                api_key=baseten_key, 
                 logging_obj=logging
             )
             if inspect.isgenerator(model_response) or (stream == True):
diff --git a/litellm/utils.py b/litellm/utils.py
index 648bb63e7..669611352 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1122,6 +1122,9 @@ def get_llm_provider(model: str, custom_llm_provider: Optional[str] = None):
         ## nlp_cloud
         elif model in litellm.nlp_cloud_models:
             custom_llm_provider = "nlp_cloud"
+        ## petals
+        elif model in litellm.petals_models:
+            custom_llm_provider = "petals"
         
         if custom_llm_provider is None or custom_llm_provider=="":
             raise ValueError(f"LLM Provider NOT provided. Pass in the LLM provider you are trying to call. E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/{model}',..)` Learn more: https://docs.litellm.ai/docs/providers")