# InputTokenDetails

> **Class** in `langsmith`

📖 [View in docs](https://reference.langchain.com/python/langsmith/schemas/InputTokenDetails)

Breakdown of input token counts.

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

## Signature

```python
InputTokenDetails()
```

## Extends

- `TypedDict`

## Constructors

```python
__init__(
    audio: int,
    cache_creation: int,
    cache_read: int,
    cache_read_over_200k: int,
    ephemeral_5m_input_tokens: int,
    ephemeral_1h_input_tokens: int,
)
```

| Name | Type |
|------|------|
| `audio` | `int` |
| `cache_creation` | `int` |
| `cache_read` | `int` |
| `cache_read_over_200k` | `int` |
| `ephemeral_5m_input_tokens` | `int` |
| `ephemeral_1h_input_tokens` | `int` |


## Properties

- `audio`
- `cache_creation`
- `cache_read`
- `cache_read_over_200k`
- `ephemeral_5m_input_tokens`
- `ephemeral_1h_input_tokens`

---

[View source on GitHub](https://github.com/langchain-ai/langsmith-sdk/blob/19dc497a3d89638e4cc35db72ea1c29cad35cbbf/python/langsmith/schemas.py#L1120)