Struct CompletionTokensDetails

pub struct CompletionTokensDetails {
    pub accepted_prediction_tokens: Option<u32>,
    pub audio_tokens: Option<u32>,
    pub reasoning_tokens: Option<u32>,
    pub rejected_prediction_tokens: Option<u32>,
}

Breakdown of tokens used in a completion.

Fields

accepted_prediction_tokens: Option<u32>

audio_tokens: Option<u32>

Audio input tokens generated by the model.

reasoning_tokens: Option<u32>

Tokens generated by the model for reasoning.

rejected_prediction_tokens: Option<u32>

When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits.

Trait Implementations

impl Clone for CompletionTokensDetails

fn clone(&self) -> CompletionTokensDetails

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for CompletionTokensDetails

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CompletionTokensDetails

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CompletionTokensDetails

fn eq(&self, other: &CompletionTokensDetails) -> 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 CompletionTokensDetails

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for CompletionTokensDetails