Nexith Core is now serving on our own sovereign GPU cluster — cache hits save up to 90%, OpenAI-compatible.Learn more →
01 / Token Plans
Capacity that fits your work.
Monthly token capacity and rate limits are configured in the Nexith control plane.
Enterprise
Unlimited / month
6,000 requests / min
4,000,000 tokens / min
No daily spend cap
02 / API Pricing
Pay for the tokens you use.
Public model rates, in USD per 1M tokens. Cached input reflects eligible cache hits.
Model
Input
Cached input
Output
Nexith Core
nexith-core
$4.00
$0.40
$20.00
How usage works
Every token has a line item.
Input tokens
Your prompt, documents and images sent to the model.
Cached input
Eligible repeated context is charged at the lower cached rate—not advertised as free.
Output tokens
The generated response, streamed or returned in one response.
Frequently asked questions
A Token Plan sets your monthly capacity and API rate limits.
Need capacity beyond standard plans?
Private deployments, custom limits and dedicated support for production teams.
Contact sales