Live fleet
Real AI traffic, served from small computers.
Offline Base runs open models on its own rack of NVIDIA Jetson Orin Nano boards, the computer inside the Base Router. Every number on this page comes straight from those boards.
Build on it
The fleet speaks the same API as OpenAI, so any app or library that takes a base URL and a key can use it. We give out free keys with a daily allowance to people who want to try building on small, local hardware. Ask for a key.
These are live readings from our own boards, so they move with the models, the length of each chat, and how busy the fleet is. A chat that is too long or too hard for a small model can be handed to a bigger cloud model; those tokens are counted separately and never in the board totals.