NEAR AI Cloud confidential inference goes live on SayGm, routed inside Intel TDX enclave
markjeffrey · x · 2026-09-21
NEAR AI Cloud's confidential inference is now live on SayGm's confidential tier. SayGm reaches dozens of models through one API key and runs its own model routing inside an Intel TDX enclave rather than ordinary servers, enabling end-to-end private inference.
Related event: NEAR AI launches confidential inference on SayGm(3 posts)→
More from Infra
- $5, 10-minute SFT on Qwen3.6-35B-A3B lifts GPQA +8% and MMLU-Pro +12% — josh_wills · 2026-09-21
- Agent runtime promises billions of agents and 10-20x sandbox density — astralmatrix · 2026-09-21
- SGLang team helps user debug hicache crash, earning community praise — TheZachMueller · 2026-09-21
- M5 Max vs $2500 desktop upgrade: real-world local LLM speed comparison — vitamins1000 · 2026-09-21
- Two years after 'intelligence too cheap to meter', $10/$50 models are the new norm — teortaxesTex · 2026-09-21
- After finding a memcached bug, Yacine says he'll switch to Valkey — yacineMTB · 2026-09-21