OpenAI

GPT Realtime 2.1

openai/gpt-realtime-2.1

realtimeaudiospeechvision

Input price

2556.7 RODI/M

~ 4 USD/M

Output price

15340.2 RODI/M

~ 24 USD/M

Context

32K

Max output

4K

Input:textaudioimage
Output:textaudio

Providers & pricing

ProviderInputOutputFree tier
Azure

Azure

Default

2556.7 RODI/M~4.00 USD/M15340.2 RODI/M
OpenAI

OpenAI

2556.7 RODI/M~4.00 USD/M15340.2 RODI/M

Pricing

RateRODIUSD (ref.)Unit
In2556.7~ 4.00USD/M · RODI/M
Out15340.2~ 24.00USD/M · RODI/M
Cached255.7~ 0.400USD/M · RODI/M
Audio in~ 32.00USD/s · RODI/s
Audio out~ 64.00USD/s · RODI/s
Image in3195.9~ 5.00USD/M · RODI/M

RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.

Capabilities

Streaming
Tool calling
Vision
JSON mode
Reasoning

About this model

OpenAI realtime voice model 2.1 over WebRTC/WebSocket/SIP with text, audio, and image inputs.

API usage

Synthesize speech with client.speech() — binary POST /v1/audio/speech.

RodiumAi SDK

speech() returns raw audio bytes (save to disk or stream to clients).

Compatible SDKs (OpenAI / Anthropic packages)