August 4, 2026
Hard caps, not alerts: how budget enforcement works
Most gateways tell you about overspend after it happens. Here's how TokenRouter blocks it at request time without slowing your traffic down.
Read postBlog
Notes on AI spend
Short, occasional writing on gateways, budgets, and running LLMs in production. No growth-hacking listicles.
July 22, 2026
Why we charge a flat fee instead of a token markup
A percentage markup means your gateway earns more when you waste more. Our incentives point the other way — here's the business logic behind $29 flat.
Read postAugust 8, 2025
Introducing TokenRouter: the financial ops gateway for LLMs
One OpenAI-compatible endpoint in front of 13 providers, with budgets that actually enforce themselves. Flat subscription, zero token markup.
Read post