SayGm Routes Prompts Through Two Attested TEEs With NEAR AI's Confidential Compute
richdotca · x · 2026-09-22
AI gateway SayGm now routes requests to NEAR AI Cloud, adding DeepSeek, GLM, Kimi, and Qwen open-weight models to a gateway that already reaches Claude, GPT, and Gemini.
NEAR AI Cloud runs inference inside Intel TDX plus NVIDIA confidential-GPU enclaves and issues a cryptographic attestation quote per request verifying which model and code ran. Through SayGm, a prompt passes through two attested TEEs, neither of which can see its contents.
The post explains what these confidential-compute guarantees actually cover, how NEAR AI requests are classified in SayGm's catalog, and what to communicate to your own users about this route's privacy properties. The API is OpenAI-compatible.
More from Infra
- Bernstein's Intel road notes: servers sold out through 2027, real test comes in 2028 — BenBajarin · 2026-09-22
- Rollout scheduling: the underappreciated infra trick boosting inference efficiency — stochasticchasm · 2026-09-22
- Grok reportedly hit by a datacenter incident, details still unclear — Daniel_Farinax · 2026-09-22
- Decoupled agent runtime, mini harnesses: notes on a frontier lab's infra stack — stochasticchasm · 2026-09-22
- Open-source decision model Laya ported to Core ML: 99.5% ops on ANE, 3.7ms per decision — alexcovo_eth · 2026-09-22
- More inference than training machines means writing will soon beat reading — GregoryDiamos · 2026-09-22