Grok 4.1 Fast Non-Reasoning

Grok 4.1 without reasoning mode.

grok-4-1-fast-non-reasoning

2,000,000 context

Starting at $0.16/M (20% off) input tokens

Starting at $0.40/M (20% off) output tokens

Streaming

Vision

Tools

JSON Output

Select Provider

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

xAI

Context: 2M

Deactivating on May 15, 2026

Input

$0.2

/M tokens

Cached

$0.05

/M tokens

Output

$0.5

/M tokens

Azure AI Foundry

Context: 2M20% off

Input

$0.2$0.16

/M tokens

Cached

—

/M tokens

Output

$0.5$0.4

/M tokens