✨ Visual Editor

close

palette Canvas & Background

Gradient:arrow_forward
Text Color:
135Β°

style Card Style

40px
16px

text_fields Typography

16px
Youssef
@0xyoussea
A new way to bill AI agents just dropped: the x402 upto scheme πŸ€–πŸ’Έ

x402 is the HTTP 402 standard for machine-to-machine payments. Until now, it only supported fixed pay-per-request pricing.

Here is why the new `upto` scheme changes everything πŸ§΅πŸ‘‡
Thread image
Youssef
@0xyoussea
The core problem with LLM-inference API payments: you rarely know the exact cost upfront.

How many tokens will an LLM generate? How much compute will an agent need?

With upto, the client authorizes a maximum amount, and the server settles for the actual amount used at the end of the request.
Youssef
@0xyoussea
This natively unlocks the most important AI and infrastructure use cases onchain:
- LLM Inference: Agent authorizes up to $5, gets charged exactly $0.42 based on tokens streamed.
- Bandwidth: Pay precisely per byte transferred.
- Compute: Charge based on actual execution time.
Youssef
@0xyoussea
At the contract level, upto uses Uniswap’s Permit2 contract to make the UX smoother and safer

The client signs a permit message offchain, then a specialized contract guarantees the server can only settle an amount that is <= the authorized maximum.
Thread image
Youssef
@0xyoussea
This is a game changer.

In previous implementations, variable onchain billing requires locking funds in escrow or streaming contracts. Capital gets stuck.

With upto, agent funds remain untouched in their wallet, free to be used elsewhere until the exact moment of settlement.
Youssef
@0xyoussea
You can start building with `upto` right now.

You can either start with the official docs or CDP's facilitator docs:
Youssef
@0xyoussea
Generated by Thread Navigator
100%
view_carousel Carousel Studio NEW
Press ⌘ + S to quick-export