Grok 4.6

grok-4.6xaiAvailableReleased 2026-08-12

xAI's smartest model, built for long-running agents plus interactive and visual work. 500K context. The listed price is the sub-200K tier; xAI doubles input and output at or above 200K tokens in a single prompt.

TextToolsThinkingThinking: low, medium, high, xhigh

Context

500K

This is the context limit available through the shared pool and may differ from the provider’s full API window.

Max output

66K

Input pricing

Official $2.00/M

Our price $0.400/M

80% off

Pricing comparison

Each route's consumer price, and what multiple of the official list price it charges. Requests start at the cheapest route and only move to the next one when it fails, so you normally pay the top rate here. Lowest ready quote is marked. USD per million tokens.

Route	Rate	Input	Output	Cache read	Cache write
Official	1x	$2.00/M	$6.00/M	$0.500/M	$2.00/M(Same as Input)
MeridianLowest	0.2x	$0.400/M	$1.20/M	$0.100/M	$0.400/M

/v1/chat/completionsAvailable