freetoken

Definition

A coined compound of "free" and "token", used as a product or method name asserting that the per-token cost or latency normally incurred has been eliminated. Like other free- compounds, the name states what was removed rather than how, so the substance — caching, speculative decoding, a pricing arrangement, an on-device path — has to be read out of the specific work. Treat it as a proper noun, not as established terminology with a settled definition.

Explainers using this term

• Paper Explained: FreeToken — Treating Your Own PC as a Single Elastic Inference PlatformFreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution