Struct TokenCounts 

pub struct TokenCounts {
    pub o200k: u32,
    pub cl100k: u32,
    pub claude: u32,
    pub gemini: u32,
    pub llama: u32,
    pub mistral: u32,
    pub deepseek: u32,
    pub qwen: u32,
    pub cohere: u32,
    pub grok: u32,
}

Token counts for multiple models

Counts are grouped by tokenizer encoding family:

• o200k: OpenAI modern models (GPT-5.x, GPT-4o, O1/O3/O4) - EXACT
• cl100k: OpenAI legacy models (GPT-4, GPT-3.5-turbo) - EXACT
• Other fields: Estimation-based counts for non-OpenAI vendors

Fields

o200k: u32

OpenAI o200k_base encoding (GPT-5.2, GPT-5.1, GPT-5, GPT-4o, O1, O3, O4)

cl100k: u32

OpenAI cl100k_base encoding (GPT-4, GPT-3.5-turbo) - legacy

claude: u32

Anthropic Claude (all versions)

gemini: u32

Google Gemini (all versions)

llama: u32

Meta Llama (3, 4, CodeLlama)

mistral: u32

Mistral AI (Large, Medium, Small, Codestral)

deepseek: u32

DeepSeek (V3, R1, Coder)

qwen: u32

Alibaba Qwen (Qwen3, Qwen2.5)

cohere: u32

Cohere (Command R+, Command R)

grok: u32

xAI Grok (Grok 2, Grok 3)

Implementations

impl TokenCounts

pub fn zero() -> Self

Create zero counts

pub fn get(&self, model: TokenModel) -> u32

Get count for a specific model

pub fn set(&mut self, model: TokenModel, count: u32)

Set count for a specific model

pub fn total(&self) -> u64

Sum all counts (useful for aggregate statistics)

pub fn add(&mut self, other: &TokenCounts)

Add counts from another TokenCounts

pub fn min(&self) -> u32

Get the minimum token count across all models

pub fn max(&self) -> u32

Get the maximum token count across all models

Trait Implementations

impl Add for TokenCounts

type Output = TokenCounts

The resulting type after applying the + operator.

fn add(self, rhs: Self) -> Self::Output

Performs the + operation.

impl Clone for TokenCounts

fn clone(&self) -> TokenCounts

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TokenCounts

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

Formats the value using the given formatter.

impl Default for TokenCounts

fn default() -> TokenCounts

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TokenCounts

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for TokenCounts

fn eq(&self, other: &TokenCounts) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for TokenCounts

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Sum for TokenCounts

fn sum<I: Iterator<Item = Self>>(iter: I) -> Self

Takes an iterator and generates Self from the elements by “summing up” the items.

impl Copy for TokenCounts

impl Eq for TokenCounts

impl StructuralPartialEq for TokenCounts