Grok 3 Mini Beta is xAI's compact reasoning model in the Grok 3 family. It provides efficient inference for tasks that need solid reasoning without the full computational overhead of the full-scale Grok 3, within a context window of 131.1K tokens.
import { streamText } from 'ai'
const result = streamText({ model: 'xai/grok-3-mini', prompt: 'Why is the sky blue?'})Grok 3 Mini Beta is the compact variant in the Grok 3 model family, released February 17, 2025. It distills the reasoning capabilities of the full Grok 3 into a smaller, more efficient architecture that reduces both latency and cost per token while still handling standard language tasks across summarization, Q&A, code, and instruction following.
The model supports a context window of 131.1K tokens and handles general-purpose tasks including summarization, question answering, code generation, and instruction following. Where the full Grok 3 targets the hardest benchmark-style reasoning tasks, Grok 3 Mini Beta fits the broad middle ground of production workloads where lower cost matters more than pushing benchmark limits.
Grok 3 Mini Beta is available at $0.3 per million input tokens and $0.5 per million output tokens through Vercel AI Gateway. For workloads that prioritize speed above all else, the Grok 3 Mini Fast variant adds further latency optimization.