Struct Usage

pub struct Usage {
    pub input_tokens: Option<usize>,
    pub input_tokens_details: Option<FxHashMap<String, usize>>,
    pub output_tokens: Option<usize>,
    pub output_tokens_details: Option<FxHashMap<String, usize>>,
    pub prompt_tokens: Option<usize>,
    pub completion_tokens: Option<usize>,
    pub total_tokens: Option<usize>,
    pub completion_tokens_details: Option<FxHashMap<String, usize>>,
}

Token usage statistics for OpenAI API requests.

This structure contains detailed information about token consumption during API requests, including both input (prompt) and output (completion) tokens. Different fields may be populated depending on the specific API endpoint and model used.

Fields

• input_tokens - Number of tokens in the input/prompt
• input_tokens_details - Detailed breakdown of input token usage by category
• output_tokens - Number of tokens in the output/completion
• output_tokens_details - Detailed breakdown of output token usage by category
• prompt_tokens - Legacy field for input tokens (may be deprecated)
• completion_tokens - Legacy field for output tokens (may be deprecated)
• total_tokens - Total number of tokens used (input + output)
• completion_tokens_details - Detailed breakdown of completion token usage

Note

Not all fields will be populated for every request. The availability of detailed token breakdowns depends on the model and API endpoint being used.

Example

use openai_tools::common::Usage;

// Create usage statistics manually (typically done by API response parsing)
let usage = Usage::new(
    Some(25),    // input tokens
    None,        // no detailed input breakdown
    Some(50),    // output tokens
    None,        // no detailed output breakdown
    Some(25),    // prompt tokens (legacy)
    Some(50),    // completion tokens (legacy)
    Some(75),    // total tokens
    None,        // no detailed completion breakdown
);

if let Some(total) = usage.total_tokens {
    println!("Request used {} tokens total", total);
}

Fields

input_tokens: Option<usize>

input_tokens_details: Option<FxHashMap<String, usize>>

output_tokens: Option<usize>

output_tokens_details: Option<FxHashMap<String, usize>>

prompt_tokens: Option<usize>

completion_tokens: Option<usize>

total_tokens: Option<usize>

completion_tokens_details: Option<FxHashMap<String, usize>>

Implementations

impl Usage

pub fn new( input_tokens: Option<usize>, input_tokens_details: Option<FxHashMap<String, usize>>, output_tokens: Option<usize>, output_tokens_details: Option<FxHashMap<String, usize>>, prompt_tokens: Option<usize>, completion_tokens: Option<usize>, total_tokens: Option<usize>, completion_tokens_details: Option<FxHashMap<String, usize>>, ) -> Self

Constructs a new Usage.

Trait Implementations

impl Clone for Usage

fn clone(&self) -> Usage

Returns a duplicate of the value.

const fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Usage

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Usage

fn default() -> Usage

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Usage

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Usage

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.