Into:Verathos
Inference that proves it ran the real model
As of · Jun 14, 12:22 UTC
A Bittensor that makes AI inference prove its own math: every answer ships with a cryptographic receipt that the correct model actually ran.
What is Verathos
Verathos is a decentralized network for running AI models where each result arrives with a cryptographic proof that the correct model actually did the computation. Instead of trusting a provider's word that you got the model you paid for, you get a mathematical receipt you can check yourself. It runs as Subnet 96 on Bittensor.
The simple version: It's like getting a tamper-proof receipt with every AI answer, proving the work was done by the model that was promised and not quietly swapped for something smaller and cheaper.
Centralized equivalent: Think Together AI or Fireworks AI for hosted model inference, but with a verification layer those services do not offer.
How it works:
- run AI models on GPUs and generate a cryptographic proof alongside each response.
- check those proofs on ordinary CPUs in milliseconds, then score each miner on whether the proof holds, plus its speed and throughput. A failed proof zeroes the score for that round.
Why This Matters
- The problem it solves: When you call a hosted AI API, you usually cannot verify which model actually served your request. A provider can route you to a smaller, cheaper model and you would not know. Verathos makes the model and the computation behind every response checkable.
Other research from the same neighborhood of the network.
