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.

Original post →

More from Infra

Infra channel →