xAI

x-ai/…

Get an API key

Every xAI model we serve, with the numbers most providers leave out — the quantisation each endpoint actually runs at, measured first-token latency, and real uptime. Model ids are copyable: pass one straight to any OpenAI-compatible client.

Grok 4.6

x-ai/grok-4.6

·xAI

xAI's frontier model, with strong coding, knowledge-work and STEM performance and a 500k-token context. Accepts text and images. Served through a third party; weights are not published.

Parameters

—

Max context

488K

Quantisation	Context	p50 TTFT	Throughput	Uptime	Input /M	Output /M	Cached in /M	Status
Undisclosed	488K	885ms	—	99.97%	$2.00	$6.00	$0.50	live

frontierlong-contextreasoningagentvisionclosed-weights

Details →

Other labs we serve

Qwen6DeepSeek3Ornith3Zz-ai3Infersia2Google1Mmeta-llama1Meta1Mminimax1OpenAI1Ttencent1Thinking Machines Lab1Xxiaomi1ZZeroEntropy1