Omniousdocs
Start hereLive V1

What is Omnious

An RFQ market for LLM inference. Your request goes to auction, providers bid to serve it, and you pay per request in USDC.

Omnious is a request-for-quote market for LLM inference. Companies running open-weight models (Llama, Qwen, DeepSeek, Mistral) stream signed price quotes into the router. When you send a query, the router runs an auction over every live quote, awards your request to the best bid on price and measured latency, and streams the reply back. Payment is pay-as-you-go USDC over the x402 protocol: no account, no API key, no subscription. A single HTTP request carries its own payment.

The name comes from the auction format. An Omnious auction is second-price and sealed-bid: the winner is paid the price at which it would have just tied the runner-up. A provider's bid decides only whether it wins, never what it is paid, which makes quoting true cost the winning strategy. That one property keeps posted prices honest without anyone policing them.

What that buys you

  • A market price, not a list price. Provider marginal costs differ with hardware, utilization, and energy prices. The auction finds the clearing price on every request instead of charging whatever a price list says this month.
  • Measured performance. The router streams every reply through its own metering proxy, so latency and token counts are measured facts, not provider claims.
  • A receipt you can audit. Every request produces a signed usage record plus a full economic breakdown: the reconstructed auction, what every rival would have charged, and the fee split.
As a customerYou never see the auction. You see one price on a 402 response, sign it, and get your reply. The market competes; you just pay less.
As a providerYou never undercut yourself. Quote your true floor; when you win, the runner-up sets your pay. Your only job is being genuinely cheap.

Start with Life of a request to see the whole flow, or jump to how the auction clears.

where this lives in code