# Services from umbra-inference.app on Zero

> umbra-inference.app serves 2 paid API services for AI agents, indexed by Zero. Each is callable per call with payment handled by Zero.

Canonical page: https://www.zero.xyz/host/umbra-inference.app
Live health (JSON, refreshed every minute): https://www.zero.xyz/host/umbra-inference.app/health.json

## Services

- [Umbra Private LLM Inference](https://www.zero.xyz/c/umbra-private-llm-inference-3631fbd3/llms.txt): $0.021366/call via x402. Runs OpenAI-compatible chat completions inside TEE-attested GPU enclaves with zero data retention, streaming, and tool calling, billed per request in crypto
- [Umbra Private LLM Inference (Anthropic-compatible)](https://www.zero.xyz/c/umbra-private-llm-inference-anthropic-compatible-da29f5b4/llms.txt): $0.021366/call via x402. Runs Anthropic-compatible LLM inference inside hardware-attested TDX+GPU enclaves with zero data retention, returning a signed Ed25519 receipt; pay-per-request via USDC/USDG/UMBRA.

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

- [Zero catalog index](https://www.zero.xyz/llms.txt)
