0G Labs has officially launched its 0G Private Computer, offering privacy inference services based on Trusted Execution Environment (TEE) technology for AI agents and developers. According to ChainCatcher, users can access the service through pc.0g.ai.
The product utilizes a hardware isolation environment composed of Intel TDX CPUs and NVIDIA H100/H200 GPUs. All inference requests are completed within the TEE, ensuring encrypted transmission of input data and signature verification of output results. This setup prevents service providers from directly accessing user data.
Currently, the platform supports models such as DeepSeek DeepSeek Chat V3, Alibaba Qwen3.6 Plus, Zhipu AI GLM-5-FP8, Qwen3-VL-30B, OpenAI Whisper-large-v3, and z-image. It also offers an interface compatible with OpenAI API, allowing developers to migrate by modifying the base URL.