La newsletter d’OpenRouter sur les données

Inferred

De nouvelles analyses sur l’utilisation des jetons d’IA, tirées de l’activité agrégée sur OpenRouter.

Toutes les éditions

Each bar is one model. Left of zero, the new router got the first token sooner.
Inferred 06

A new routing engine

This week - the router. On Wednesday we shipped the biggest change to provider routing since OpenRouter began. Instead of mostly sending traffic to the cheapest provider, the router now weighs speed and reliability alongside price for every request.

  • Faster first touch
  • Fewer rate limits
  • Faster streams
  • Across the whole experiment, median time to first token fell 16.9% and the share of requests hitting a 429 roughly halved, for 6.0% more cost per request.
Lire l’édition

Également dans cette édition

Requests that hit a 429 before succeeding. Each point is a 3-hour block.Each row is one model: gray is the legacy router, blue the new one.Open-weight chat requests by who chose the provider, October 28 to 29, 2026.