Official Provider HubSan Francisco, CA, USA

xAI API Pricing & Token Economics

xAI develops the Grok model family (Grok 4.6 flagship, Grok 2, and Grok 2 mini). Built for extreme mathematical reasoning, real-time web awareness, and coding workflows, xAI APIs feature 131k to 500k token context windows, a 50% asynchronous batch discount on Grok 4.6, and compatibility with OpenAI SDK specifications.

Official xAI Pricing Docs API Reference

Prompt Caching Policy

Batch / Asynchronous Rules

Standard API execution rules. Refer to individual endpoint rate limits for asynchronous processing.

Special Billing Conditions

Zero write fees on standard prefix evaluation; automatic cache invalidation.

Active xAI Models(4 models verified)

All 39 Models →

Model	Context	Input / 1M	Cached / 1M	Output / 1M	Batch Discount	Actions
Grok 4.6 grok-4.6	500k	$2.00	$0.50	$6.00	50% off	Specs →
Grok 2 grok-2	128k	$2.00	—	$10.00	N/A	Specs →
Grok 2 mini grok-2-mini	128k	$0.20	—	$1.00	N/A	Specs →
Grok 4.6 Mini grok-4.6-mini	512k	$0.40	$0.10	$1.60	50% off	Specs →

Calculate your monthly xAI bill

Simulate prompt caching hit rates, batch discounts, and output token costs with zero server logging.

Open Cost Calculator →