Anthropic released FlashProve on November 2, 2026, a research prototype that produces a cryptographic proof that one specific language model generated one specific reply, per the company's research post "Progress on provable inference for large language models," which carries a November 2 date and shows an update on November 3. The prototype targets large Mixture-of-Experts (MoE) language models and relies on a zkSNARK, a zero-knowledge succinct argument of knowledge. Anthropic built it with researchers at EPFL, MIT, and StarkWare. The team tested it on Llama 4 Maverick, a 400-billion-parameter MoE model, and measured it against vLLM running the same model in FP8 on eight H100 GPUs. The overhead came out at about 72 times per GPU across runs and about 94 times at the heaviest tested load. The team released the prover, two verifiers, the formal proofs, and a protocol specification under the Apache 2.0 license. The researchers describe the work as intermediate progress, not a finished program, and TechCrunch reported that there are no plans to deploy FlashProve at Anthropic or at another lab. No pricing, no commercial availability, and no customer deployment has been announced.