docs(cost): rewrite stale completion_cost docstring (#47022)

The old docstring called completion_response required, said total_time was in
seconds (it is milliseconds), and only covered a handful of the parameters.
Replace it with a short accurate summary and fix the "calculat" typo in the
unmapped-model error.

Co-authored-by: Kerry Lu <kerry@berri.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

litellm/cost_calculator.py

@@ -1438,32 +1438,15 @@ def completion_cost(
     vertex_location: str | None = None,  # for Vertex AI regional-endpoint uplift (e.g. "us-east5", "global")
 ) -> float:
     """
-    Calculate the cost of a given completion call fot GPT-3.5-turbo, llama2, any litellm supported llm.
+    Return the USD cost of a LiteLLM call.
 
-    Parameters:
-        completion_response (litellm.ModelResponses): [Required] The response received from a LiteLLM completion request.
+    Pass `completion_response` to price a response LiteLLM returned. Without one, pass `model` plus
+    `messages` / `prompt` and `completion`, and token counts are computed from the text. Prices come from
+    `litellm.model_cost` unless `custom_cost_per_token` or `custom_cost_per_second` is given. `total_time`
+    is in milliseconds and only matters for per-second pricing such as Replicate and SageMaker.
 
-        [OPTIONAL PARAMS]
-        model (str): Optional. The name of the language model used in the completion calls
-        prompt (str): Optional. The input prompt passed to the llm
-        completion (str): Optional. The output completion text from the llm
-        total_time (float, int): Optional. (Only used for Replicate LLMs) The total time used for the request in seconds
-        custom_cost_per_token: Optional[CostPerToken]: the cost per input + output token for the llm api call.
-        custom_cost_per_second: Optional[float]: the cost per second for the llm api call.
-
-    Returns:
-        float: The cost in USD dollars for the completion based on the provided parameters.
-
-    Exceptions:
-        Raises exception if model not in the litellm model cost map. Register model, via custom pricing or PR - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json
-
-
-    Note:
-        - If completion_response is provided, the function extracts token information and the model name from it.
-        - If completion_response is not provided, the function calculates token counts based on the model and input text.
-        - The cost is calculated based on the model, prompt tokens, and completion tokens.
-        - For certain models containing "togethercomputer" in the name, prices are based on the model size.
-        - For un-mapped Replicate models, the cost is calculated based on the total time used for the request.
+    Raises if no candidate model name resolves to pricing. Register the model via `litellm.register_model`
+    or add it to model_prices_and_context_window.json.
     """
     try:
         call_type = infer_call_type(call_type, completion_response) or "completion"
@@ -2066,7 +2049,7 @@ def completion_cost(
                 )
                 if idx == len(potential_model_names) - 1:
                     raise e
-        raise Exception(f"Unable to calculat cost for received potential model names - {potential_model_names}")
+        raise Exception(f"Unable to calculate cost for received potential model names - {potential_model_names}")
     except Exception as e:
         raise e