NEAR AI Cloud launches confidential inference on SayGm, both sides run in Intel TDX enclaves

bittingthembits · x · 2026-09-21

NEAR AI Cloud's confidential inference is now live on SayGm's confidential tier. SayGm reaches dozens of models through a single API key and runs its own routing inside an Intel TDX enclave instead of ordinary servers; NEAR AI Cloud runs the model inside a TDX enclave too. With two operators in the path, neither has visibility into the request, delivering end-to-end private inference.

Related event: NEAR AI launches confidential inference on SayGm(3 posts)→

Original post →

More from Infra

Infra channel →