get_usage_metadata_callback#

langchain_core.callbacks.usage.get_usage_metadata_callback(name: str = 'usage_metadata_callback') → Generator[UsageMetadataCallbackHandler, None, None][source]#

Beta

This feature is in beta. It is actively being worked on, so the API may change.

Get context manager for tracking usage metadata across chat model calls using AIMessage.usage_metadata.

Parameters:

name (str) – The name of the context variable. Defaults to "usage_metadata_callback".

Return type:

Generator[UsageMetadataCallbackHandler, None, None]

Example

from langchain.chat_models import init_chat_model
from langchain_core.callbacks import get_usage_metadata_callback

llm_1 = init_chat_model(model="openai:gpt-4o-mini")
llm_2 = init_chat_model(model="anthropic:claude-3-5-haiku-latest")

with get_usage_metadata_callback() as cb:
    llm_1.invoke("Hello")
    llm_2.invoke("Hello")
    print(cb.usage_metadata)

{'gpt-4o-mini-2024-07-18': {'input_tokens': 8,
  'output_tokens': 10,
  'total_tokens': 18,
  'input_token_details': {'audio': 0, 'cache_read': 0},
  'output_token_details': {'audio': 0, 'reasoning': 0}},
 'claude-3-5-haiku-20241022': {'input_tokens': 8,
  'output_tokens': 21,
  'total_tokens': 29,
  'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}

Added in version 0.3.49.