Pricing

Pay for tokens.
Not for waiting.

Usage-based pricing on the fastest model on Earth. Runs inside AWS and GCP, in your region — one API call, nothing to deploy.

Most popular Pay as you go
$2/ M input tokens
$6/ M output tokens

Full-speed celeris-1. Pay only for what you use.

  • +Usage-based billing, no minimums
  • +Production rate limits
  • +Streaming, OpenAI-compatible API
  • +Email support
Get started
Enterprise
Custom

For teams running Celeris on the critical path at scale.

  • +Volume pricing & dedicated clusters
  • +Custom rate limits
  • +SSO · SOC 2 · VPC deployment
  • +Solutions engineering, dedicated support & SLA
Contact sales

Prices in USD. Billed per million tokens; input and output metered separately.

Questions, answered.

Q.01

Which model do I get?

Full-speed celeris-1 on every plan. Same weights, same speed, same quality — what you test is exactly what you ship.

Q.02

Do I pay more for lower latency?

No. Speed is the product, not a premium tier. Every request on every plan runs at full speed.

Q.03

How does billing work?

Per million tokens, input and output metered separately. No minimums, no reserved capacity, no idle GPU charges.

Q.04

Can we run it inside our own cloud?

Enterprise plans can deploy in your VPC, in your region, so requests never leave your cloud's network.

Start in minutes.
Scale when you're ready.