GPT Realtime 2

GPT Realtime 2 responds to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.

Input price
$4.40
Output price
$26.40
Context
128K
Max output
32K
Modalities
InputTextAudioImageOutputTextAudio
—
—
Released
2026-05-06
Knowledge cutoff
—
Try in ChatCompare

Providers

This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].

Included providers1
  • SuccessTTFT
  • OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

Input
$4.40
per 1M tokens
Output
$26.40
per 1M tokens
Cache read
$0.44
per 1M tokens
Audio input
$35.20
per 1M tokens
Audio output
$70.40
per 1M tokens
Image input
$5.50
per 1M tokens
audio.input.cached
$0.44
image.io.input.cached
$0.55

Similar models

Other models with the same output types at a similar price.

  • Better value: more capable, lower price
  • Pareto frontier
  • Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GPT Realtime 2This model
—
Input
$4.40
Output
$26.40
Claude Opus 5.5
168
Input
$4.40
Output
$22.00
GPT Realtime 2.1
—
Input
$4.40
Output
$26.40
Kimi K3.1 Pro HighSpeed
—
Input
$4.1756–$4.40
Output
$21.8416–$22.00
Llama 3.1 405B Instruct
129
Input
$3.85
Output
$3.85