zkAPI

Vitalik

2026-10-04 00:12:33

Vitalik says he is testing local AI, zkAPI and Tor to get personalized health advice

Ethereum co-founder Vitalik said in a post on X that he is running a self-experiment aimed at getting personalized diet and exercise recommendations from advanced AI models without exposing private information to remote systems. The setup uses a local Qwen 3.8 Flash Next model as the coordinator, while more powerful remote models are called as tools. To reduce privacy leakage, the design relies on the local model to draft queries, zkAPI to separate payment identity, and Tor to isolate network and IP information. Vitalik said the system is already working and has returned recommendations, but he also outlined several trade-offs. According to his post, Tor is not well suited for unlinking requests one by one, and latency can run 10x to 100x above the ideal level. He added that the current request-construction strategy is still not good enough. Qwen 3.8 Flash Next is currently running at about 20 to 30 TPS, while speeds above 100 TPS would make the setup feel meaningfully faster. He also noted a basic constraint of the approach: the more carefully users limit what remote models can see, the less help those remote models can provide.

Vitalik Buter

2026-10-04 01:35:12

Vitalik tests local-model orchestration for remote AI with a three-layer privacy setup

Vitalik Buterin said he is running a personal experiment that uses health and travel data to generate diet and exercise recommendations while trying not to expose private information to frontier AI models. In the setup he described, a local model, Qwen 3.8 Flash Next, acts as the orchestrator, while remote large language models are used as tools to make up for weaker reasoning and knowledge on the local side. The privacy design has three layers: the local model rewrites queries to reduce identity and writing-style leakage, zkAPI is used so payment rails do not reveal identity, and Tor is used to hide network metadata and IP addresses. Buterin said he has already received recommendations and that remote models improved the output. He also pointed to several shortcomings in the current design, including Tor being a poor fit for linking requests, privacy that may still fall short, latency running 10x to 100x above what it should be, suboptimal skill-file strategy, local-model throughput of roughly 20 to 30 TPS, and a trade-off where giving remote models less data also reduces how much they can help.

Vitalik

2026-10-04 00:29:43

Vitalik says he is testing a privacy-preserving AI setup using local and remote models

Vitalik.eth said in a Farcaster post that he is running a personal experiment that combines a local model with a remote frontier model to generate personalized diet and exercise suggestions from personal health and travel data while keeping privacy protections in place. According to the post, the system uses a three-layer privacy design. At the identity layer, a local Qwen 3.8B model builds the query request on the user’s behalf so writing style does not reveal identity. At the payment layer, zkAPI is used to hide payment information. At the network layer, Tor is used to conceal the IP address. Vitalik said the system is already working end to end, but he also listed three shortcomings: Tor is inefficient and introduces high latency for per-request unlinkability, the local model currently runs at only 20-30 TPS while a smooth experience would require 100+ TPS, and tighter data protection reduces how much help the remote model can provide. The related code has been submitted to Ethereum’s zkAPI repository.

Ethereum

2026-10-02 03:38:57

Ethereum Foundation launches zkAPI on mainnet for privacy-preserving AI API payments

The Ethereum Foundation has rolled out zkAPI on Ethereum mainnet, introducing a payment system that lets users and AI agents pay API fees with onchain assets such as ETH and USDC while reducing the risk that payment identities are directly tied to API usage records. Built with the Open Anonymity Project, zkAPI works by having users deposit funds into a vault smart contract and then prove, through zero-knowledge proofs, that they have enough balance to pay without revealing which deposit or wallet is being used. The design does not require an onchain transaction every time an AI model is called. After funds are deposited, proof verification happens mainly offchain, and the system issues API keys with time and spending limits. The Ethereum Foundation is also pushing x402 as a separate payment standard for AI agents, with zkAPI focused on unlinkability rather than full anonymity. The foundation has not disclosed user numbers, API payment volume, or protocol revenue, leaving the product in an early infrastructure stage.

Ethereum Foun

2026-10-01 23:43:41

Ethereum Foundation launches zkAPI on mainnet for ETH and USDC-funded API payments

The Ethereum Foundation has launched zkAPI on the Ethereum mainnet, according to The Block. The system is based on a design co-authored by Vitalik Buterin and is built to let users pay for artificial intelligence services and other APIs with pre-deposited ETH or USDC. The payment flow uses zero-knowledge proofs, allowing users to fund requests without exposing a direct link between the payer and the specific API call.\n\nThe report says service providers using zkAPI cannot associate a given request with the person who made the payment. That separates payment information from usage data at the service layer. The rollout places the mechanism directly on Ethereum mainnet and frames it as an onchain payment option for API access.\n\nNo additional launch details, usage figures, or rollout timeline beyond the mainnet deployment were disclosed in the source material.

Ethereum Foun

2026-10-01 19:30:59

Ethereum Foundation and Open Anonymity launch zkAPI on mainnet to hide API payment identity

The Ethereum Foundation and the Open Anonymity Project have launched zkAPI, a system now live on Ethereum mainnet that uses zero-knowledge proofs to separate API usage from payment identity. Under the setup, users can deposit assets such as ETH or USDC into an on-chain vault, then authorize either one-time or session-based API access with a zero-knowledge proof. Service providers can confirm that payment is valid, but they cannot see where the deposit came from or who made the payment. At the same time, the payment layer cannot view the content of the request. The project is currently aimed mainly at AI inference workloads, though the design can also be extended to services such as RPC and image generation. Funds are held in smart contracts, and users can exit and withdraw their assets on their own. Techub attributed the item to Wu Blockchain.