GPT-Realtime-1.5
import { gateway } from '@ai-sdk/gateway';
export async function POST() { const { token, url } = await gateway.experimental_realtime.getToken({ model: 'openai/gpt-realtime-1.5', });
return Response.json({ token, url, tools: [] });}Copy link to headingPlayground
Try out GPT-Realtime-1.5 by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
GPT-Realtime-1.5Voice agent
Talk to a realtime agent. It listens to your voice and replies with audio.
Start the session and ask the agent something.
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingMore models by OpenAI
| Model |
|---|
| 1.1M | 2.0s | 168tps | $1/M$0.20/M +1 more | $6/M$1.20/M +1 more | Read: $0.1/M$0.02/M+1 more Write: $1.25/M$0.25/M+1 more | $10/K + input costs | +4 |   | 07/09/2026 | ||||
| 1.1M | 3.2s | 95tps | $5/M+1 more | $30/M+1 more | Read: $0.5/M+1 more Write: $6.25/M+1 more | $10/K + input costs | +4 | | 07/09/2026 | ||||
| 1.1M | 1.1s | 149tps | $2.50/M$2/M +1 more | $15/M$12/M +1 more | Read: $0.25/M$0.2/M+1 more Write: $3.13/M$2.5/M+1 more | $10/K + input costs | +4 | | 07/09/2026 | ||||
| 1.1M | 0.9s | 113tps | $2.50/M+1 more | $15/M+1 more | Read: $0.25/M+1 more Write: — | $10/K + input costs | +4 | | 03/05/2026 | ||||
| 400K | 6.0s | 118tps | $0.05/M | $0.40/M | Read:$0.01/M Write:— | $14/K + input costs | +3 | | 08/07/2025 | ||||
| 131K | 0.1s | 469tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — |   +5 | 08/05/2025 |
Copy link to headingAbout GPT-Realtime-1.5
GPT-Realtime-1.5 launched on February 23, 2026 as OpenAI's flagship realtime audio model for voice agents and customer support. Compared with earlier realtime preview models, GPT-Realtime-1.5 delivers stronger instruction following, more reliable tool calling, and better voice quality.
Speech-to-speech is the defining design choice. Rather than chaining transcription, a text model, and speech synthesis, GPT-Realtime-1.5 processes audio natively and responds in audio. That cuts latency and produces responses that sound more natural. Tool calling works during live conversation, so a voice agent can check a calendar or query a database while the caller is still talking.
GPT-Realtime-1.5 also enacts specified roles reliably, following instructions to hold a particular personality or tone. That consistency makes GPT-Realtime-1.5 practical for branded support experiences and scripted workflows at scale.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Realtime support on AI Gateway is in beta through AI SDK 7. The integration is WebSocket-based: your server mints a short-lived token, and the browser connects with the AI SDK's realtime hook, which handles microphone capture and playback. Your AI Gateway API key never reaches the client.
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use GPT-Realtime-1.5
Best for
- Customer support agents: Script-following voice agents that answer, resolve, and escalate correctly
- Tool-calling voice workflows: Assistants that check calendars, query databases, or call APIs mid-conversation
- Low-latency voice interfaces: Native speech-to-speech avoids the delay of chained transcription and synthesis
- Role-consistent personas: Agents that hold a defined personality or tone across long sessions
Consider alternatives when
- Deeper reasoning required:
gpt-realtime-2adds configurable reasoning effort for complex voice workflows - Recorded audio transcription:
gpt-4o-transcribeandgpt-4o-mini-transcribeare built for speech-to-text jobs - Cost-sensitive voice features:
gpt-realtime-minihandles high-volume, simpler interactions at a lower rate
Copy link to headingConclusion
GPT-Realtime-1.5 is the production baseline for voice agents through AI Gateway: native speech-to-speech, reliable tool calling, and consistent instruction following. Build here first, and move specific workflows to gpt-realtime-2 when they need configurable reasoning.