The Veil
Every AI request today leaves a paper trail.
Prompts retained
Providers log every prompt and response by default, indefinitely, for training and “safety.”
Identity linked
API keys and accounts tie every request back to a real identity — no way to ask anonymously.
Trust, not proof
Privacy policies promise good behavior. Nothing lets you verify what actually happened to your data.
The Protocol
How a request runs inside LETHE, unread by anyone.
Encrypted request
Your prompt is encrypted client-side and paid for via x402 — no account, no API key tied to your identity.
Attested execution
The model runs inside a Trusted Execution Environment; even LETHE's own infrastructure cannot read the prompt or the output.
Verifiable deletion
A cryptographic attestation proves the request ran in an isolated enclave and was discarded — not just promised, provable.
See It Run
One request in, one response out, nothing remembered.
One OpenAI-compatible endpoint, callable from cURL, TypeScript, or Python. Encrypted request, attested execution inside a TEE, verifiable deletion — the same flow described in The Protocol, made real in three lines of code.
Explore API Docs →const res = await fetch("https://api.lethe.ai/v1/infer", {
method: "POST",
headers: {
Authorization: `x402 ${payment}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "llama-3.1-70b",
enclave: "tee-us-1",
messages: [{ role: "user", content: prompt }],
}),
});
The Token
Stake $LETHE, earn your share of every call.
Stakers earn protocol revenue. Every call burns supply. The more LETHE is used, the scarcer it gets.
A share of every call
Stake $LETHE to earn a share of the USDC paid through x402 for every inference call on the network.
Deflationary by design
A portion of $LETHE is burned with every call, permanently shrinking supply as usage grows.
Our Product
Private inference infrastructure for agents and developers.
Cognition
Your prompts and completions are never visible outside the enclave running them.
Perception
No dashboard, no logs, no operator with access to your requests — not even us.
Timing
Every call is paid and settled in the moment via x402 — nothing left behind after.
Network
Built for agents talking to agents, machine to machine, over the OpenAI API.
Begin
Your first request can already be private.
No account to create, no waitlist to join. Pay per call in USDC via x402 and run inference inside an attested enclave today.