LangChain Reference home page

GitHub
Main Docs

Overview
Caches
Callbacks
Documents
Document loaders
Embeddings
Exceptions
Language models
Serialization
Output parsers
Prompts
Rate limiters
Retrievers
Runnables
Utilities
Vector stores

MCP Adapters

Standard Tests

Text Splitters

⌘I

LangChain Assistant

Ask a question to get started

Enter to send•Shift+Enter new line

Menu

Overview Caches Callbacks Documents Document loaders Embeddings Exceptions Language models Serialization Output parsers Prompts Rate limiters Retrievers Runnables Utilities Vector stores

Language

Theme

Pythonlangchain-coremessagesaiInputTokenDetails

Class●Since v0.3

InputTokenDetails

Copy

InputTokenDetails()

Bases

TypedDict

Constructors

Attributes

View source on GitHub

constructor

__init__

Name	Type
audio	int
cache_creation	int
cache_read	int

Audio input tokens.

cache_creation: int

Input tokens that were cached and there was a cache miss.

Since there was a cache miss, the cache was created from these tokens.

cache_read: int

Input tokens that were cached and there was a cache hit.

Since there was a cache hit, the tokens were read from the cache. More precisely, the model state given these tokens was read from the cache.

Breakdown of input token counts.

Does not need to sum to full input token count. Does not need to have all keys.

Example:

{
    "audio": 10,
    "cache_creation": 200,
    "cache_read": 100,
}

May also hold extra provider-specific keys.