Umbra

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.

InferenceUnknowneip155:84532Exactvia facilitator:payAI
AiLlmInferencePrivacyTee
Activity
—
Nothing indexed for this service or its provider yet. Not a claim that it is unused — only that we hold no record.
—
Verified settled volume
0 settlements proven x402 by their on-chain EIP-3009 marker.
$0.0001
Listed price
As published in the catalog. Always read the live 402 before paying.
—
Calls · 30d
Upstream's own call count for this endpoint, not ours.
—
Unique payers · 30d
Never called
—
Upstream on-chain volume
Reported by the source catalog.
Paid to
0x8B89C727ad99c664A79e761B4A309A92b658dd92

The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.

Asset 0x036CbD53842c5426634e7929541eC2318f3dCF7e

Provider

The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.

Accepts

The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.

0.0001USDC≈ $0.0001 USD
on Base Sepolia · exact scheme

Pay 0.0001 USDC on Base Sepolia to 0x8B89…8dd92. The signed payment is good for 2.1 minutes.

USD Coin (Base Sepolia) contract
0x036C…dCF7e
Payment window
2.1 minutes
As published
100 smallest units
The catalog’s raw entry
[
  {
    "asset": "0x036CbD53842c5426634e7929541eC2318f3dCF7e",
    "extra": {
      "name": "USDC",
      "version": "2"
    },
    "payTo": "0x8B89C727ad99c664A79e761B4A309A92b658dd92",
    "amount": "100",
    "scheme": "exact",
    "network": "eip155:84532",
    "maxTimeoutSeconds": 124
  }
]

Extensions

{
  "bazaar": {
    "info": {
      "input": {
        "body": {
          "model": "deepseek/deepseek-v4-flash-0731",
          "messages": [
            {
              "role": "user",
              "content": "In one sentence, what is HTTP 402?"
            }
          ],
          "max_tokens": 300
        },
        "type": "http",
        "method": "POST",
        "bodyType": "json"
      },
      "output": {
        "type": "json",
        "example": {
          "umbra": {
            "receipt": {
              "cost": {
                "settled": "0.000045",
                "currency": "USDG"
              },
              "tier": "sealed",
              "model": "deepseek/deepseek-v4-flash-0731",
              "retained": {
                "prompt_bytes": 0,
                "response_bytes": 0
              },
              "attestation": {
                "gateway": {
                  "tee": "tdx"
                },
                "model_runtime": {
                  "tee": "tdx+gpu"
                }
              }
            },
            "signature": {
              "alg": "ed25519"
            }
          },
          "usage": {
            "prompt_tokens": 18,
            "completion_tokens": 20
          },
          "choices": [
            {
              "message": {
                "role": "assistant",
                "content": "HTTP 402 Payment Required is a status code reserved for digital payment schemes."
              },
              "finish_reason": "stop"
            }
          ]
        }
      }
    },
    "schema": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "input"
      ],
      "properties": {
        "input": {
          "type": "object",
          "required": [
            "type",
            "method",
            "bodyType",
            "body"
          ],
          "properties": {
            "body": {
              "type": "object",
              "required": [
                "model",
                "messages"
              ],
              "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"
                }
              }
            },
            "type": {
              "type": "string",
              "const": "http"
            },
            "method": {
              "enum": [
                "POST"
              ],
              "type": "string"
            },
            "bodyType": {
              "enum": [
                "json",
                "form-data",
                "text"
              ],
              "type": "string"
            }
          },
          "additionalProperties": false
        },
        "output": {
          "type": "object",
          "required": [
            "type"
          ],
          "properties": {
            "type": {
              "type": "string"
            },
            "example": {
              "type": "object"
            }
          }
        }
      }
    }
  }
}

Provenance

Seen in the source catalog
2026-10-26 01:00Z
Last indexed by Roundhouse
2026-10-31 07:45Z
Last enriched (probe, favicon, geo)
—
x402 version
2
Max timeout
124s
Liveness probe
Not probed
Report

Hand this page to an agent

Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.

GET api.roundhouseai.io/v0/endpoints

Nothing indexed for this service or its provider yet. Not a claim that it is unused — only that we hold no record. Verified volume counts only settlements with an on-chain EIP-3009 marker.

Open skill.md
Show the prompt
Using Roundhouse, look up the x402 service Umbra and tell me whether it is
worth paying: what a call costs, whether the endpoint answered when last probed, and what
its payment record actually shows.

curl -s 'https://api.roundhouseai.io/v0/endpoints?q=Umbra'
curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>'

Then call it: read the price from the live 402 at https://umbra-inference.app/v1/chat/completions, never from
a cached figure, and pay with an x402 client.

The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except
/v0/unified* and /v0/endpoints. Either pay over x402 (mint a personal key for $0.01 at
GET https://api.roundhouseai.io/v0/test/x402), or ask me for an organization key, which I create at
https://preview.roundhouseai.io/dashboard/connections. If you have neither, ask before going further.

If you do not have Roundhouse tools or skills installed, read
https://preview.roundhouseai.io/skill.md first — it is the whole procedure.