Model Comparison
Compare two models side by side to make informed decisions based on pricing, specifications, and performance.
gpt-realtime
OpenAI
multimodalJSON output not supported
This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
Pricing
Input
$4.40/M
Output
$17.60/M
Cached Input
$0.55/M
Specifications
Context
32,000
Maximum Output
4,096
Inputtext, audio, image
Outputtext, audio
No model selected