Why sell on Omnious

Your marginal cost is your edge. Second-score clearing means quoting your true floor is the profitable strategy.

The marginal cost of serving a token is not one number. It moves with your hardware generation, your utilization this hour, how well your batches fill, and what you pay for energy. Two providers serving the same open-weight model can sit several-fold apart in cost per token, and the same provider can be cheap at 9am and expensive at noon.

A posted-price router cannot express any of that. A static list price has to cover your worst hour, so it overprices your best ones, and it never rewards you for the batching work that actually lowered your cost. An auction can. On Omnious you stream a signed quote every couple of seconds, repriced as your GPUs fill and drain, and every request clears against the book as it stands right now. Your cost advantage becomes fills the moment it exists.

You are paid the tie price, not your bid

Clearing is second-score: the winner is paid the price at which its score would have exactly tied the runner-up. Every term in your payment is a rival's ask and router-measured latencies. Your own bid appears nowhere in it, so your quote decides whether you win, never what you are paid.

That makes truthful cost-quoting the dominant strategy, by construction rather than by policy. Quote above your cost and you lose fills you would have profited on, without raising the price of the fills you keep. Quote below cost and you win requests that pay less than serving them. Quote your true marginal cost floor and every fill you win clears at or above it. There is no bid-shading game to play, so there is no strategy team to fund.

The router takes 7%, and only 7%

The router's fee is 7% of cleared volume, deducted from your netted payout at epoch close. It never spread-takes: there is no gap between what the customer pays and what you receive beyond that published fee, and every receipt carries the exact fee split down to the base unit. A router that earned on spread would want prices opaque. This one earns by growing volume, so its incentive is a tight, liquid, transparent book. See fees and unit economics for the full accounting.

Measured latency beats marketing claims

The latency term in your auction scoreis measured by the router's own streaming proxy on every fill, not read from your marketing page. If you are genuinely fast, you win fills against rivals whose claims outrun their hardware, and you never have to publish a benchmark to prove it. New providers start on a pessimistic 1500 ms prior and earn their way down; idle providers get periodic probe requests so a good number never goes stale just because you were not winning traffic.

The result is a market where the things that should win, low real cost and low real latency, are the things that do win. If you run well-utilized hardware behind vLLM or SGLang, that is your edge, and this is the venue built to pay for it. Start with the onboarding runbook.