Launch HN: Tokenless (YC S26) – Automatic model switching to save money

In one line

Tokenless is a model router and drop-in replacement for the OpenAI and Anthropic APIs — the same quality at less than half the cost.

Opening excerpt

Token less The router that cuts your inference bill in half . A drop-in replacement for your API calls — always routed to the right model.

Most calls don’t need a frontier model. Tokenless fans out your request to a group of models and watches them think. Once a model is clearly on track, we select it and cancel the other models, and you only pay for what you need.

We expose an OpenAI and Anthropic compatible endpoint. Point your models at us and get started today!

time → confidence, per model this request $0.0000 $0.0000 sent to Fable 5 $0.0000 $0.0000 − 52 % · $0.0101 never billed Measured , not marketed. Solve rate and cost per task on public agentic benchmarks, against the best published run of each frontier model.

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (46 points / 40 comments, via usetokenless.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.