Enum RealtimeModel 

#[non_exhaustive]
pub enum RealtimeModel {
    GptRealtime2_1,
    GptRealtime2_1Mini,
    GptRealtime2,
    GptRealtime,
    GptRealtimeMini,
    GptRealtime1_5,
    GptRealtimeTranslate,
    GptRealtime_2025_08_28,
    Custom(String),
}

Models available for the Realtime API.

This enum covers all models that can be used with the Realtime API for real-time audio and text interactions via WebSocket.

Available Models

• [GptRealtime_2025_08_28]: GPT Realtime model (default)

Example

use openai_tools::common::models::RealtimeModel;

let model = RealtimeModel::GptRealtime_2025_08_28;
assert_eq!(model.as_str(), "gpt-realtime-2025-08-28");

Reference

See OpenAI Realtime API Documentation

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

GptRealtime2_1

gpt-realtime-2.1 - Reasoning speech-to-speech model with tool use

• Context: 128K tokens, 32K max output
• Improved alphanumeric recognition, silence/noise handling and interruption behavior

GptRealtime2_1Mini

gpt-realtime-2.1-mini - Smaller, cheaper gpt-realtime-2.1

GptRealtime2

gpt-realtime-2 - Previous generation realtime voice model

GptRealtime

gpt-realtime - Alias tracking the current realtime voice model

GptRealtimeMini

gpt-realtime-mini - Cost-efficient realtime voice model

GptRealtime1_5

gpt-realtime-1.5 - Earlier realtime voice model

GptRealtimeTranslate

gpt-realtime-translate - Streaming speech-to-speech translation

Uses the v1/realtime/translations endpoint rather than v1/realtime.

GptRealtime_2025_08_28

gpt-realtime-2025-08-28 - GPT Realtime model (default)

Kept as the default so that existing callers of RealtimeClient::new() keep reaching the same model. Select a newer model explicitly with RealtimeClient::model.

Custom(String)

Custom model ID for new models not yet in enum

Implementations

impl RealtimeModel

pub fn as_str(&self) -> &str

Returns the model identifier string for API requests.

pub fn custom(model_id: impl Into<String>) -> Self

Creates a custom model from a string.

Trait Implementations

impl Clone for RealtimeModel

fn clone(&self) -> RealtimeModel

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RealtimeModel

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

Formats the value using the given formatter.

impl Default for RealtimeModel

fn default() -> RealtimeModel

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RealtimeModel

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for RealtimeModel

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

Formats the value using the given formatter.

impl Eq for RealtimeModel

impl From<&str> for RealtimeModel

fn from(s: &str) -> Self

Converts to this type from the input type.

impl Hash for RealtimeModel

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for RealtimeModel

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for RealtimeModel

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 RealtimeModel