GPU Hour
A GPU hour measures compute usage as one graphics processor running for one hour.
Category
AI Compute Markets
These terms describe how AI workloads measure, serve, route, and pay for compute in centralized or decentralized markets.
How to recognize this theme
Words used when model workloads buy or route compute capacity.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Serving Endpoint
A serving endpoint is the network address where an application sends requests to a hosted AI model.
Model Router
A model router selects which model or provider should handle a request based on cost, latency, quality, or policy.
Compute Escrow
Compute escrow holds payment until a compute provider delivers agreed work or required evidence for an AI workload.