get_token_cost_for_model#

langchain_nvidia_ai_endpoints.callbacks.get_token_cost_for_model(model_name: str, num_tokens: int, price_map: dict, is_completion: bool = False) float[source]#

Get the cost in USD for a given model and number of tokens.

Parameters:
  • model_name (str) – Name of the model

  • num_tokens (int) – Number of tokens.

  • price_map (dict) – Map of model names to cost per 1000 tokens. Defaults to AI Foundation Endpoint pricing per https://www.together.ai/pricing.

  • is_completion (bool) – Whether the model is used for completion or not. Defaults to False.

Returns:

Cost in USD.

Return type:

float