Confidential Router
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
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Confidential Router Alternatives
Explore 168 products in the Inference APIs category. View all Confidential Router alternatives.
DeepInfra
Serverless API for 200+ open-weight models on DeepInfra's own US hardware, priced per token.
Inceptron
EU-hosted LLM inference with an in-house compiler: serverless open-weight model APIs and dedicated GPU deployments
LibertAI
Decentralized, privacy-first inference API running open-source LLMs in trusted execution environments
Mistral
Use models in a few clicks with our platform. Download our open models for deep access.
Work on Confidential Router? Feature it at the top of Inference APIs.
Is your product missing?