GPT Realtime · fastrouter

This is OpenAI's general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections. Supports a 32,000 token context window and up to 4,096 output tokens per response (knowledge cutoff: Oct 01, 2023). Also supports image input (text/audio/image → text/audio).

Base modelAll models on this baseAll models of the providerto the provider

All OpenAI models at every provider

Input, $/1M $32.00

Output, $/1M $64.00

Cache read $0.40

Cache write —

Context 32 000

Max output 4 096

Accepts audio, images, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page