> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Enum Cache Read Accounting

> How cache-read tokens relate to prompt token counts in provider usage.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi`.

```rust
pub enum CacheReadAccounting {
    IncludedInPromptTokens,
    Separate,
}
```

How cache-read tokens relate to prompt token counts in provider usage.

## Variants

### `IncludedInPromptTokens`

<pre />

`cache_read_tokens` are already included in `prompt_tokens`.

### `Separate`

<pre />

`cache_read_tokens` are separate from `prompt_tokens`.

## Trait Implementations

### `impl Clone for CacheReadAccounting`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for CacheReadAccounting`

<pre />

#### `fmt`

<pre />

### `impl<'de> Deserialize<'de> for CacheReadAccounting`

<pre />

#### `deserialize`

<pre />

### `impl PartialEq for CacheReadAccounting`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for CacheReadAccounting`

<pre />

#### `serialize`

<pre />

### `impl Copy for CacheReadAccounting`

<pre />

### `impl Eq for CacheReadAccounting`

<pre />

### `impl StructuralPartialEq for CacheReadAccounting`

<pre />