Thesis
Why us
One model can be offered at more than 15 venues, each venue with its own offerings and prices. That's how a commodity market looks like. So one way to work out this problem is to reason about it the way people do in the financial markets. The LLM inference market is quickly becoming a market similar to corporate bonds and we want to be at the forefront of how it trades. See the live price table →
| Corporate bonds | Inference |
|---|---|
| The instrument, what you are buying | |
| Issuer, the company | The model and its weights |
| The issue, one specific CUSIP | The exact served configuration you buy from one host |
| No bond equivalent, a commodity grade, like sulfur in crude or protein in wheat | Quantization (fp16 / fp8 / int4), the same artifact at a measurably different spec, not a discount |
| Block size, how much clears at once | Context window |
| Settlement convention (T+1 vs T+2) | Service tier, real-time vs batch, contracted up front |
| The market, who quotes, and how you buy | |
| Dealer / market maker | The inference provider, quotes continuously, holds inventory, earns a spread |
| Dealer inventory | GPU capacity |
| Asking several dealers for a price (RFQ) | What a router does, every request |
| On-the-run vs off-the-run | Newest model vs last generation, same curve, ~60× faster |
| The fill, what you actually got, and only measurement shows it | |
| Default risk | Error rate, the fill that never arrives |
| Time to fill, slippage | Realized time to first token, and its variance |
| Ratings agencies | Model evals, they grade the issuer, never the fill |
| TRACE, the post-trade tape | What we're building: a tape for inference |
