Pricing

You only pay for the tokens we remove from your input.

Pro

For production workloads

Included in Pro:

  • All compression models
  • Personalized compression models
  • Priority support
  • Dedicated Slack support
Get a quote

Enterprise

Full control, in your cloud or ours

Everything in Pro, plus:

  • Forward deployed engineering support
  • Full control over data residency
  • Advanced security & compliance
  • Option for on-premise deployment in your VPC
  • Personalized compression models
Talk to us

How we calculate pricing

Example: 10M tokens in, 4M removed with compression, 6M out to your LLM.

Your input
10M tokens
Sent to your LLM
6M tokens
You're charged for
4M tokens removed

We only charge a compression cost from the tokens we remove. We make sure you always save money.

Ready to get started?

Book a 30-minute call and we'll get you set up with an API key.

Book a time