01 — API Pricing Index

Every LLM price,
on one honest scale.

Input, output, and cached-input rates for the models developers actually ship on — normalized to USD per million tokens, so comparison is finally apples-to-apples.

Project my monthly bill → How it works

Index Summary USD / 1M

02 — The Table

All models, sorted your way

SORT

Model Provider Context Input Output Cached in

{{ count }} / {{ total }} models Cached input billed at ~10% of standard input rate.

Representative figures compiled July 2026 from provider documentation, for planning only. Always confirm current rates on the provider's own pricing page before committing spend.

Every LLM price,on one honest scale.

All models, sorted your way

Every LLM price,
on one honest scale.