Premium private inference

Pricing and limits

Three monthly private inference plans for ultra-fast, privacy-first access. Settlement currency: USD.

Choose your plan

Monthly private inference plans

All plans bill monthly in USD with privacy-first processing and clear capacity tiers.

Premium

Build at inference speed.

For focused builders shipping private AI workloads with privacy-first processing and predictable monthly access.

$0/month
Join the waitlist

Features

Flash — 1200 tok/s

Privacy-first processing

Prompts and responses are not used for training

Growth

Most popular

Move production workloads faster.

For production workloads that need more monthly capacity without trading away speed or data control.

$0/month
Join the waitlist

Features

Flash — 1200 tok/s

5x usage

Privacy-first processing

Prompts and responses are not used for training

Scale

Highest capacity

Private by design. Built to scale.

For demanding private inference workloads that need our highest monthly capacity with privacy-first processing.

$0/month
Join the waitlist

Features

Flash — 1200 tok/s

20x usage

Privacy-first processing

Prompts and responses are not used for training

Background

Plans are monthly USD and limited to the approved cohort while the service is at capacity. There is no free trial, no coupon, and no postpaid credit. Join the waitlist for access.