Grok 3 Fast Beta is the speed-optimized variant of xAI's Grok 3 model. It delivers lower latency inference while keeping the same Grok 3 training foundation, with a context window of 131.1K tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-3-fast', prompt: 'Why is the sky blue?'})| Model |
|---|
| 1M | 0.8s | 94tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — |  | 04/30/2026 | ||||
| 2M | 0.4s | 134tps | $1.25/M | $2.50/M | Read: $0.2/M Write: — | $5/K + input costs | — | | 03/09/2026 | ||||
| 2M | 0.7s | 53tps | $0.20/M | $0.50/M | Read: $0.05/M Write: — | $5/K + input costs | — | | 09/19/2025 | ||||
| 256K | 0.3s | 74tps | $0.20/M | $1.50/M | Read:$0.02/M Write:— | — | — | | 08/28/2025 | ||||
| 2M | 0.6s | 65tps | $0.20/M | $0.50/M | Read: $0.05/M Write: — | $5/K + input costs | — | | 07/09/2025 | ||||
| 2M | 5.8s | 119tps | $0.20/M | $0.50/M | Read: $0.05/M Write: — | $5/K + input costs | — | | 07/09/2025 |