Icon for Confidential Router

Confidential Router

Free Trial

OpenAI-compatible LLM API that serves open-weight models inside hardware-attested confidential environments

Confidential Router is an OpenAI-compatible LLM API from Super Protocol. It serves open-weight models inside trusted execution environments on AMD SEV-SNP or Intel TDX CPUs and NVIDIA Confidential Computing GPUs. Prompts and completions are not stored.

Gatekeeper, an open-source local proxy, checks the signed attestation before any request leaves your machine. Access is by invite, with $100 of starting credit. The catalogue is Gemma 2 2B and Llama 3.2 3B for now, from $0.02 per million input tokens.

Pricing: Per token usage

Pricing $0.02/1M input tokens
HQ 🇺🇸 United States
Screenshot of Confidential Router webpage

Work on Confidential Router? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →