Grok-3 Fast

Optimized Grok-3 variant for lower latency.

grok-3-fast

STABLEModel DeactivatedGet Started View uptime

131,072 context

Starting at $5.00/M input tokens

Starting at $25.00/M output tokens

Streaming

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: 131.1k

Deprecated since Aug 8, 2025Deactivated since Sep 15, 2025

Input

/M tokens

Cached

—

/M tokens

Output

$25

/M tokens

AI-powered help

Please introduce yourself before we start.