rename max_tokens.json

docs/my-website/docs/token_usage.md

@@ -5,7 +5,7 @@ However, we also expose 3 public helper functions to calculate token usage acros
 
 - `token_counter`: This returns the number of tokens for a given input - it uses the tokenizer based on the model, and defaults to tiktoken if no model-specific tokenizer is available. 
 
-- `cost_per_token`: This returns the cost (in USD) for prompt (input) and completion (output) tokens. It utilizes our model_cost map which can be found in `__init__.py` and also as a [community resource](https://github.com/BerriAI/litellm/blob/main/cookbook/community-resources/max_tokens.json).
+- `cost_per_token`: This returns the cost (in USD) for prompt (input) and completion (output) tokens. It utilizes our model_cost map which can be found in `__init__.py` and also as a [community resource](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json).
 
 - `completion_cost`: This returns the overall cost (in USD) for a given LLM API Call. It combines `token_counter` and `cost_per_token` to return the cost for that query (counting both cost of input and output). 
 

docs/my-website/src/pages/token_usage.md

@@ -5,7 +5,7 @@ However, we also expose 3 public helper functions to calculate token usage acros
 
 - `token_counter`: This returns the number of tokens for a given input - it uses the tokenizer based on the model, and defaults to tiktoken if no model-specific tokenizer is available. 
 
-- `cost_per_token`: This returns the cost (in USD) for prompt (input) and completion (output) tokens. It utilizes our model_cost map which can be found in `__init__.py` and also as a [community resource](https://github.com/BerriAI/litellm/blob/main/cookbook/community-resources/max_tokens.json).
+- `cost_per_token`: This returns the cost (in USD) for prompt (input) and completion (output) tokens. It utilizes our model_cost map which can be found in `__init__.py` and also as a [community resource](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json).
 
 - `completion_cost`: This returns the overall cost (in USD) for a given LLM API Call. It combines `token_counter` and `cost_per_token` to return the cost for that query (counting both cost of input and output). 
 

litellm/__init__.py

@@ -36,7 +36,7 @@ caching_with_models = False  # if you want the caching key to be model + prompt
 cache: Optional[Cache] = None # cache object
 model_alias_map: Dict[str, str] = {}
 def get_model_cost_map():
-    url = "https://raw.githubusercontent.com/BerriAI/litellm/main/cookbook/community-resources/max_tokens.json"
+    url = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
     
     try:
         response = requests.get(url)

litellm/tests/test_completion_cost.py

@@ -16,7 +16,7 @@
 
 
 # print(completion_cost(
-#         model="togethercomputer/llama-2-70b-chat", 
+#         model="togethercomputer/llama-2-2b-chat", 
 #         prompt="gm", 
 #         completion="hello"
 #     ))

litellm/utils.py

@@ -652,7 +652,9 @@ def completion_cost(
     prompt_tokens = token_counter(model=model, text=prompt)
     completion_tokens = token_counter(model=model, text=completion)
     if "togethercomputer" in model:
-        together_catgeory = get_model_params_and_category(model)
+        # together ai prices based on size of llm
+        # get_model_params_and_category takes a model name and returns the category of LLM size it is in model_prices_and_context_window.json 
+        model = get_model_params_and_category(model)
         # print(together_catgeory)
     prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar = cost_per_token(
         model=model, prompt_tokens=prompt_tokens, completion_tokens=completion_tokens
@@ -875,7 +877,7 @@ def get_max_tokens(model: str):
     try:
         return litellm.model_cost[model]
     except:
-        raise Exception("This model isn't mapped yet. Add it here - https://raw.githubusercontent.com/BerriAI/litellm/main/cookbook/community-resources/max_tokens.json")
+        raise Exception("This model isn't mapped yet. Add it here - https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json")
     
 
 def load_test_model(