Grok Voice Think Fast 2.0
import { gateway } from '@ai-sdk/gateway';
export async function POST() { const { token, url } = await gateway.experimental_realtime.getToken({ model: 'xai/grok-voice-think-fast-2.0', });
return Response.json({ token, url, tools: [] });}Playground
Try out Grok Voice Think Fast 2.0 by xAI. 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.
Grok Voice Think Fast 2.0Voice agent
Talk to a realtime agent. It listens to your voice and replies with audio.
Start the session and ask the agent something.
Providers
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.
More models by xAI
| Model |
|---|
| 500K | 1.7s | 68tps | $2/M+1 more | $6/M+1 more | Read: $0.3/M+1 more Write: — | $5/K + input costs | +3 | | 07/08/2026 | ||||
| 256K | 1.3s | 136tps | $1/M+1 more | $2/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +2 | | 05/20/2026 | ||||
| 1M | 1.1s | 84tps | $1.25/M+1 more | $2.50/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +3 |  | 04/30/2026 | ||||
| 2M | 0.5s | 150tps | $1.25/M+1 more | $2.50/M+1 more | Read: $0.2/M+1 more Write: — | $5/K + input costs | +3 | | 03/10/2026 | ||||
| 1M | 1.3s | 182tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | +2 | | 11/19/2025 | ||||
| 1M | 0.4s | 174tps | $0.20/M | $0.50/M | Read:$0.05/M Write:— | — | +1 | | 11/19/2025 |
About Grok Voice Think Fast 2.0
Grok Voice Think Fast 2.0 is xAI's realtime voice model, released July 29, 2026 and available through AI Gateway. Audio goes in and audio comes back, so Grok Voice Think Fast 2.0 handles full-duplex conversation without a chain of separate transcription, text, and speech models. xAI reports improvements over the previous Grok Voice model in reasoning, transcription accuracy, and conversation.
Grok Voice Think Fast 2.0 reasons in parallel with speech, working through a query while the conversation keeps moving. Grok Voice Think Fast 2.0 also spends fewer reasoning tokens than the previous Grok Voice model, so tool calls fire sooner, often before the agent finishes its first sentence. Transcription holds up in real-world conditions, including background noise and telephony compression.
Through AI Gateway, a server route mints a short-lived token so your API key never reaches the client, and the useRealtime hook from @ai-sdk/react drives the WebSocket, microphone capture, and playback from the browser, with session config for voice, turn detection, instructions, and tools. Realtime support is in beta and ships on the canary releases of the AI SDK, and you can try Grok Voice Think Fast 2.0 in the AI Gateway playground at https://ai-sdk.dev/playground/xai:grok-voice-think-fast-2.0.
What To Consider When Choosing a Provider
- Configuration: Grok Voice Think Fast 2.0 supports speech-to-speech only. Realtime sessions don't transcribe or translate recorded files, so use
grok-sttfor that. Image input isn't supported in realtime sessions either. - Configuration: AI Gateway enforces session limits: 25 minutes maximum duration, a five-minute idle timeout, a 30-second window for the first client message, and a 256 KB cap on message size. Teams also have a limit on concurrent sessions. Reconnecting doesn't resume a previous session, so replay any context you need after a drop. Realtime support is in beta and ships on canary AI SDK releases, so expect API changes.
- 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.
When to Use Grok Voice Think Fast 2.0
Best for
- Realtime Voice Agents: Full-duplex conversation with spoken replies while the user talks
- Phone And Support Lines: Transcription that holds up under background noise and telephony compression
- Early Tool Calling: Lower reasoning overhead fires tool calls within the first spoken sentence
- Reasoning During Conversation: Parallel thinking works through hard queries while speech continues
- Grok Voice Upgrades: A step up from Grok Voice Think Fast 1.0 on the same realtime surface
Consider alternatives when
- Recorded Audio Transcription:
grok-stttranscribes files, since realtime sessions are speech-to-speech only - One-Way Speech Output:
grok-ttsgenerates narration without a live session - Long Uninterrupted Sessions: AI Gateway caps realtime sessions at 25 minutes, so plan reconnect logic
- Text-Only Conversations: A text model such as Grok 4.5 costs less when no audio is involved
Conclusion
Grok Voice Think Fast 2.0 brings xAI's second-generation realtime voice model to AI Gateway, with reasoning that runs alongside speech, earlier tool calls, and transcription that survives noisy phone audio. Mint a token on the server, connect with the useRealtime hook, and see current pricing on this page.