{"uid":"cap_OhZ9o0xCqA_LYodFp8mC0","slug":"umbra-private-llm-inference-3631fbd3","name":"Umbra Private LLM Inference","description":"Private LLM inference, OpenAI-compatible. Sealed open models in TDX + GPU enclaves or Claude; streaming and tool calling; signed Ed25519 receipt naming the attested enclaves; zero retention. Pay per request in USDG, USDC (Base, Solana) or UMBRA.","url":"https://umbra-inference.app/v1/chat/completions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"model id from GET /v1/models (sealed: open models in TDX + GPU enclaves; standard: Claude)"},"tools":{"type":"array","description":"OpenAI function tools"},"stream":{"type":"boolean","description":"server-sent events; paid upfront, unused ceiling refunded on-chain"},"messages":{"type":"array","description":"OpenAI chat messages (system, user, assistant, tool)"},"max_tokens":{"type":"integer","description":"output cap; sets the price ceiling quoted in the 402"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.021366","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.021366/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.021366","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.021366","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_HBhYop43gCiHwlzhJPSGK","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.021366","costPer":"request","priority":0,"asset":"0x5fc5360D0400a0Fd4f2af552ADD042D716F1d168","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs OpenAI-compatible chat completions inside TEE-attested GPU enclaves with zero data retention, streaming, and tool calling, billed per request in crypto","exampleAgentPrompt":"Using a private, zero-retention LLM with attestation, send a system message 'You are a helpful assistant' and user message 'Summarize the key risks of smart contract audits' using the sealed open model, streaming the response with a max of 512 tokens.","exampleUseCases":[{"title":"Confidential legal document drafting","prompt":"I need to draft a sensitive NDA clause — use a privacy-preserving LLM that won't retain my data or logs, run it in a sealed enclave, and give me a signed receipt proving it ran securely. Use the sealed model, max 1024 tokens, with my system prompt 'You are an expert contract lawyer.'"},{"title":"Private AI tool calling in an agent","prompt":"Call the private inference API in sealed mode with tool calling enabled — I need my agent to invoke a weather function tool and summarize the result, with zero data retention and a signed attestation receipt, capped at 512 output tokens."},{"title":"Streaming Claude responses with privacy guarantees","prompt":"Stream a response from Claude using the Umbra standard model — system message: 'You are a coding tutor', user message: 'Explain Rust ownership in simple terms' — with zero retention and max 800 tokens, so I can display the answer as it arrives."}],"resultDescription":"An OpenAI-compatible chat completion response (streamed or non-streamed) containing the model's generated text and any tool calls, plus a signed Ed25519 receipt identifying the attested TDX+GPU enclaves that processed the request. Zero data is retained after the response.","failureModes":["Invalid or unsupported model ID — endpoint returns an error listing valid model IDs from GET /v1/models","Insufficient crypto balance or payment failure — 402 response with price ceiling not met","max_tokens too large for model context window — request rejected with validation error","Streaming connection dropped mid-response — partial tokens received, unused ceiling refunded on-chain","Tool schema malformed — function calling fails with schema validation error","Enclave attestation unavailable — service degraded, may fall back to non-sealed mode or error"],"whenToPreferThis":"Choose Umbra when your workload requires verifiable privacy guarantees: the prompt and response must not be logged or stored by any party, you need a cryptographic proof (Ed25519 signed receipt) that inference ran inside a hardware-attested TEE enclave, and you are comfortable paying per request in stablecoins or UMBRA token. Also prefer this when you need OpenAI-compatible tool calling and streaming with these privacy properties, or when working in regulated domains (legal, medical, financial) where data residency and zero-retention are non-negotiable.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-31T06:38:12.765Z","isFirstParty":false,"canonicalSlug":"umbra-private-llm-inference-3631fbd3"}