> 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.

# Struct Tokenization Metadata

> Token count metadata for a prompt block.

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

<pre />

Token count metadata for a prompt block.

Records the model family and token count so that downstream phases can compute cache-aware token budgets.

## Fields

### `model_family: String`

Model family used for tokenization (e.g., "claude", "gpt").

### `token_count: u32`

Number of tokens in the block content.

## Trait Implementations

### `impl Clone for TokenizationMetadata`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for TokenizationMetadata`

<pre />

#### `fmt`

<pre />

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

<pre />

#### `deserialize`

<pre />

### `impl PartialEq for TokenizationMetadata`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for TokenizationMetadata`

<pre />

#### `serialize`

<pre />

### `impl StructuralPartialEq for TokenizationMetadata`

<pre />