The OpenRouter data newsletter

Inferred

Fresh insights on AI token usage, drawn from aggregate activity across OpenRouter.

All editions

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

Inferred 06LatestOct 30, 2026

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.

Read edition

Also in this edition

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.

Share of family requests on an older version, and share of accounts using one.

Inferred 05Oct 23, 2026

Version lag

This week - version lag. Or put another way, why the hell are some people still using Claude Sonnet 4.5?

A quarter of requests run on an older version
Nearly a third of accounts use an outdated model
Latest isn’t always cheapest

Read edition

Also in this edition

Latest version share of family requests, by days since launch.

Change in cost if older-version traffic moved to the latest version, at list prices.

Models used per month, by percentile, AI-native startups and large orgs.

Inferred 04Oct 15, 2026

Model portfolios

This week - a deep dive into AI-native startups and large organizations on OpenRouter. How many models do they use, how much of the work goes to their main model, how often do they swap that main model out, and which tasks hold on to a model the longest.