Umbra
POST https://umbra-inference.app/v1/chat/completions
Listed in PayAI
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.
Other endpoints from umbra-inference.app
The same service's other paid functions that Hagglyai tracks, each with its own price. Functions outside Hagglyai's categories are not listed.
| Endpoint | Category | Price per call |
|---|---|---|
| GET /v1/chat/completions | LLM inference | $0.0004 |
How to buy
This endpoint takes pay-per-call payments over x402. Call it once without paying to see its live price; any x402 client then pays and retries automatically.
curl -i -X POST "https://umbra-inference.app/v1/chat/completions"
# HTTP/1.1 402 Payment Required: price, asset and payTo are in the responseEstimated calls per day
Paid calls to umbra-inference.app's tracked endpoints each day, estimated from the 30-day totals the x402 catalogues report. Each bar is the change in that 30-day total since the day before, plus the calls that left the 30-day window (taken as an average day). It is an estimate: Hagglyai does not measure or pay for these calls.
No usage reported for any of 3 tracked endpoints. Unknown usage is left out, not counted as zero.
Compared with other providers
Coverage matters: a provider whose endpoints report more of their usage can rank higher.
| # | Provider | Reported 30-day calls | Coverage |
|---|---|---|---|
| 1 | blockrun.ai | 96,560 | 30 of 36 endpoints |
| 2 | x402.orthogonal.com | 5,352 | 193 of 256 endpoints |
| 3 | api.gondola-ai.com | 4,430 | 1 of 3 endpoints |
| 4 | agent402.tools | 3,764 | 147 of 231 endpoints |
| 5 | api.surplusintelligence.ai | 1,487 | 1 of 2 endpoints |
| 6 | api.losbeto.xyz | 1,351 | 21 of 108 endpoints |
| 7 | api.strale.io | 827 | 33 of 36 endpoints |
| 8 | saylorinnovations.com | 568 | 181 of 224 endpoints |