Anthropic's FlashProve lets users cryptographically verify which AI model answered them
Progress on provable inference for large language models
Anthropic released FlashProve, an open-source prototype for provable inference using zkSNARKs. For Llama 4 Maverick, a 400B-parameter mixture-of-experts model, a single H100 GPU generates proofs at over 100 tokens per second, with roughly 19 MB per 1,024-token request — about 70-95 times the GPU time vLLM needs. The proofs hide model weights and let users, auditors, and regulators confirm a response came from the claimed model. Code, Lean proofs, and a technical report are out under Apache 2.0.
An attacker who compromises a server, or a model that substitutes itself for another, must then produce valid proofs for the expected weights to avoid detection, which they cannot do.