Skip to content

Grok 3 Mini Fast Beta

Grok 3 Mini Fast Beta is the fastest and most cost-efficient model in xAI's Grok 3 family. It combines the compact Grok 3 Mini architecture with speed optimization for maximum throughput at the lowest per-token cost.

Tool Use
index.ts
import { streamText } from 'ai'


const result = streamText({
  model: 'xai/grok-3-mini-fast',
  prompt: 'Why is the sky blue?'
})
OverviewPlaygroundAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ
Latency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.