Skip to content
Dashboard

gpt-realtime-2

gpt-realtime-2 is OpenAI's most capable realtime voice model, bringing configurable reasoning effort, stronger instruction following, and more reliable tool use to speech-to-speech voice agents. Your use subject to OpenAI's Terms & Privacy Policies.

Websockets
index.ts
import { gateway } from '@ai-sdk/gateway';
export async function POST() {
const { token, url } = await gateway.experimental_realtime.getToken({
model: 'openai/gpt-realtime-2',
});
return Response.json({ token, url, tools: [] });
}

More models by OpenAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1.1M
1.4s
163tps
$1/M
$6/M
Read:
$0.1/M
Write:
$1.25/M
$10/K
+ input costs
+4
azure logo
bedrock logo
openai logo
07/09/2026
1.1M
3.2s
73tps
$5/M
$30/M
Read:
$0.5/M
Write:
$6.25/M
$10/K
+ input costs
+4
azure logo
bedrock logo
openai logo
07/09/2026
400K
4.5s
205tps
$0.05/M
$0.40/M
Read:$0.01/M
Write:
$14/K
+ input costs
+3
azure logo
openai logo
08/07/2025
400K
3.1s
132tps
$0.25/M
$2/M
Read:$0.03/M
Write:
$14/K
+ input costs
+3
azure logo
openai logo
08/07/2025
131K
0.2s
481tps
$0.35/M
$0.75/M
Read:$0.25/M
Write:
baseten logo
bedrock logo
cerebras logo
+5
08/05/2025
131K
0.2s
897tps
$0.07/M
$0.30/M
Read:$0.04/M
Write:
bedrock logo
deepinfra logo
fireworks logo
+4
08/05/2025