> 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 Token Pricing Rates

> Token rates expressed as USD per one million tokens.

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

<pre />

Token rates expressed as USD per one million tokens.

## Fields

### `input_per_million: f64`

Uncached prompt/input token price.

### `output_per_million: f64`

Completion/output token price.

### `cache_read_per_million: Option<f64>`

Cached prompt/input token read price.

### `cache_write_per_million: Option<f64>`

Prompt cache write price.

## Trait Implementations

### `impl Clone for TokenPricingRates`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for TokenPricingRates`

<pre />

#### `fmt`

<pre />

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

<pre />

#### `deserialize`

<pre />

### `impl PartialEq for TokenPricingRates`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for TokenPricingRates`

<pre />

#### `serialize`

<pre />

### `impl Copy for TokenPricingRates`

<pre />

### `impl StructuralPartialEq for TokenPricingRates`

<pre />