The VoltageGPU Playground sends your contract to an open-weight -TEE model that runs inside Intel TDX: a TEE model from our catalog on Free, Plus and Starter, Qwen3.5-397B-TEE on Pro and Enterprise. Sign-in is required. Documents pass through our servers to a TDX enclave and are not kept. Outputs are not legal advice. The underlying API at api.voltagegpu.com/v1 is OpenAI-compatible: point your existing OpenAI SDK at the new base URL and your prompts run on -TEE models in Intel TDX.
The playground is the lightweight surface. For production, point CrewAI, LangChain, OpenAI SDK or any MCP client at the same OpenAI-compatible endpoint. Your agent code runs wherever you want; inference runs on -TEE models in Intel TDX. See BYOA confidential AI.
Prompts reach our API over TLS; we relay them to a third-party TEE inference network where the model runs in Intel TDX, without storing them. The host's hypervisor cannot read enclave memory.
Drop a PDF or text contract. The analysis runs on a -TEE model in Intel TDX, with memory encrypted by the CPU. Documents pass through our servers to a TDX enclave and are not kept. Outputs are not legal advice.
Drop your contract here
PDF · TXT · CSV · up to 4 MB · scanned PDFs are not supported