Anthropic reports progress on provable inference for large language models

Anthropic said it has made progress on provable inference for large language models, releasing a research prototype called FlashProve that is designed to cryptographically prove a response came from a specified model. In its Nov. 2, 2026 announcement, the company said the system can generate proofs for Llama 4 Maverick at around 110 tokens per second on a single H100 GPU, with a proof size of about 19 MB per 1,024-token request. According to Anthropic, provable inference is intended to address a basic verification problem: users today cannot reliably tell from output alone whether a response came from the model they intended to query. The company said the approach could support consumer applications, internal security use cases and efforts to verify compliance with AI pacing requirements.

BeCrypto News shows a short excerpt and links to the publisher. The full report belongs to Blockchain.News.