Skip to content

Grok 4.1 Fast Non-Reasoning

Grok 4.1 Fast Non-Reasoning is xAI's speed-optimized Grok 4.1 Fast model for agentic tool calling. It delivers direct responses without reasoning overhead across a context window of 1M tokens, engineered for high-throughput agent workflows.

Tool UseFile InputVision (Image)Implicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'xai/grok-4.1-fast-non-reasoning',
prompt: 'Why is the sky blue?'
})
Throughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.