Ethereum Foundation Unveils zkAPI for Private AI Inferences

The Ethereum Foundation and The Open Anonymity Project have released zkAPI, a tool that enables private AI inferences using zero-knowledge proofs. This technology decouples financial accounting from user identity during the consumption of commercial large language models.

Traditionally, accessing neural compute services via application programming interfaces required linking credit cards or static API credentials to every request, exposing users' prompt histories directly to infrastructure providers. In contrast, zkAPI shifts spending authorization to a local cryptographic balance known as a private note.

Users execute a one-time deposit into a smart contract on the Ethereum mainnet and generate zero-knowledge proofs certifying available funds without exposing the funding origin or remaining account balance. The system then generates a temporary key with a dollar-denominated spending cap, routing queries directly to the inference provider without billing intermediaries.

The protocol anchors its security in the Groth16 scheme over the BN254 curve and utilizes Poseidon hashes to verify commitments and nullifiers. This design prevents double-spending of compute credits without compromising user anonymity on-chain.