Better Insights Faster Metrics And New Developer Power Tools
Source
OpenRouter
Author
OpenRouter
Date
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
OpenRouter now measures reasoning-model latency to the first reasoning tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → and counts reasoning tokens in throughput, so published speed numbers mean something different. A category filter on the models API returns models tuned for programming and other categories.
