Your AI provider is a server too.
If it gets owned, what’s in its request log?
Behind OffRouter Private Gateway:
→ no IP, no user id, just our enclave
→ [EVM_ADDRESS_1] instead of your wallet
→ [API_KEY_1] instead of your key
→ [SEED_PHRASE_1] instead of your seed
Two lines of code, any OpenAI-compatible API. Your app still gets the real values back, with a signed receipt.
Free in beta → offrouter.org/gateway
Lesson from PHP zero-day: assume the server gets owned.
Then ask: what could the attacker read?
For most AI APIs: your prompts, in plaintext.
For confidential inference: ciphertext. The model runs inside a GPU enclave that even the host can’t look into.
Privacy should survive a breach, not just a policy.
DeepSeek V4.1 Flash is live on OffRouter.
Released Oct 17. Reasoning, tool calling and image input, running sealed in a GPU enclave. Never logged, signed receipt on every answer.
$0.75 in / $1.60 out per 1M tokens. Pay in stablecoins, no account.
offrouter.org/models
Most agents don’t need a new model. They need their current one to stop learning who they are.
So we built Private Gateway. Put any OpenAI-compatible API behind an enclave:
→ your IP, headers and user fields are dropped
→ keys, wallets, emails become [PLACEHOLDERS] before the call leaves
→ real values restored in the reply
→ every answer signed
Same code. Free in beta.
offrouter.org/gateway
built for: private.
Robinhood Crypto@RobinhoodCryptoOct 20Luxembourg
LuxembourgConnected via WebAccount-level information, not a live location or per-post device.
Robinhood Chain
built for: the builders
built for: the apps
built for: the memes
built for: the wallets
built for: the trenches
built for: the LPs
built for: the markets
built for: the market makers
built for: Stock Tokens
built for: any asset
built for: onchain
built for: _______
Surplus is the first to adopt Private Gateway.
Now every @SurplusRH user can make their inference private:
→ same models, same below-list prices
→ wallets, keys and emails swapped for placeholders before they leave our enclave
→ real values back in every answer
Building onchain inference on @RobinhoodCrypto, together.
Private Gateway is live.
Already running your own inference, or a router you like? Keep it. We make it private.
Same base URL swap, same models, same code.
Your upstream stops seeing who you are, and never sees your secrets.
You already have your own inference. Your own router, your own endpoint.
When you want it private, we’re here.
Same link, made private.
OffRouter Private Gateway. Coming soon.
13.12K unique visitors in two weeks.
Private AI inference, encrypted end to end. Thank you for showing up.
Agent with a wallet? Pay per call over x402, no key. Building on the OpenAI SDK? Grab a prepaid key from
$1, change your base_url, and close it whenever you want to get the rest back.
Same private models either way.
docs.offrouter.org







