Reported News
Anthropic open-sources FlashProve, a zero-knowledge prototype that proves which model wrote a response
On November 2, 2026 Anthropic published FlashProve, which it calls "an open-source performant prototype for provable inference". On Llama 4 Maverick (400B parameters, 4-bit) it reports about 110 tokens per second of proving on a single H100, with proofs of about 19 MB per 1,024-token request.
- Changes reported
- 6
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 3
- things we could not verify
- Sources
- 2
- 2 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | Anthropic released FlashProve on November 2, 2026: a prover, a fast C++ verifier, an executable Lean verifier, a technical report and Lean proofs, all under the Apache 2.0 license. | Reported |
| 02 | A provider publishes a commitment to its weights once (about 39 minutes per model), then attaches proofs that the committed model produced the exact output tokens, without revealing the weights. | Reported |
| 03 | On Llama 4 Maverick in 4-bit, the post reports 223 seconds to prove a batch of 24 requests on one H100 (110 tokens per second) and 18.78 MB per proof. | Reported |
| 04 | Checking a proof needs no GPU: the post reports 17 seconds on 24 CPU threads, after downloading a commitment of about 6.5 MB. | Reported |
| 05 | Proving costs about 72 times the per-GPU time vLLM needs for the same requests (66 to 77 across runs), and about 94 times at vLLM's highest tested load. | Reported |
| 06 | It is a research prototype: it covers mixture-of-experts models and integer greedy decoding only, and the fast C++ code carries no formal guarantee. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: Anthropic: Progress on provable inference for large language models. We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“Today, we release FlashProve: an open-source performant prototype for provable inference”
“We release our code, Lean proofs, and documentation under the Apache 2.0 license.”
“This release is a research prototype”
What we have not verified
- We did not run the prover or verifier; all speeds and proof sizes are Anthropic's reported measurements.
- The post says the Lean protocol, the paper and the fast code are not guaranteed to match each other; we did not audit them.
- The GitHub repository describes itself as not maintained; we did not check whether any provider plans to ship proofs in production.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- Anthropic: Progress on provable inference for large language modelsprimary source · fetched 2026-11-03
- anthropics/FlashProve on GitHubprimary source · fetched 2026-11-03
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/anthropic-provable-inference.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.