The same open-weights model is sold by a dozen providers at prices ~10× apart and latencies that vary several-fold. Corporate bonds traded the same way until a tape made the fills public. This page is the full mapping, the map of where the venues sit, and where the analogy breaks.
The same model (say Llama-3.3-70B) is served by 15+ providers at up to ~10× price dispersion and 5–20× latency variance. That's a commodity market structure. We think it should be priced and executed like one. The people who execute in a commodity market best are the ones who've spent years pricing, executing, and measuring latency inside one. The live price table is on the overview →
Bonds are the closest market for how inference is transacted: dealer-quoted, heterogeneous, priced by asking several dealers, and until TRACE in 2002, with no public record of what actually traded. Spreads were wide because nobody could see them. For what a token is, electricity is the better guide: produced on demand, consumed on delivery, impossible to store.
| 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 |
Inference has ratings agencies for the issuer and no tape for the fill.
The dividing line is the point: everything above “the fill” is contracted before you buy, and you can read it off a price page. Everything below it only exists after the request runs, and nobody publishes it. That is the whole argument for a tape. Where bonds run out, and it matters: a bond's deliverable is a fixed cash flow, so only the odds of receiving it vary, credit ratings grade the issuer's ability to pay, never the quality of what arrives. A token's deliverable itself varies. That's a commodity-grade problem, and an unsolved one: CME publishes exactly what “No. 2 Yellow Corn” means before anyone can trade it, while three of five providers quoting the same price for a model don't disclose the grade they ship. And a bond can be resold where a token cannot, which removes one specific mechanism: nobody can buy cheap tokens and sell them dear, so there is no arbitrageur forcing quotes together. (Not permanently: a contract on future tokens is transferable even though the token isn’t. Electricity forwards trade for exactly that reason, but writing one requires a defined deliverable first.) What remains is the other convergence mechanism (buyers switching venue) and that one is blocked by information, not by physics: you can only move your traffic to the better venue if someone publishes which venue was better. That is the argument for a tape, in one sentence. TRACE needed neither. It added no bid side and no matching engine, published what actually traded, and spreads compressed anyway.
Kottos AI is building exchange-grade infrastructure for LLM inference: an open-source microsecond gateway today, real-time intelligence that establishes best price-performance next, and (as GPU compute financializes) price discovery for inference capacity itself. The open core is how you start; the routing intelligence is where it compounds.
The same open-weights model (Llama, DeepSeek, Qwen) is served from datacenters coast to coast. Distance is latency: the Bay Area and Virginia are ~60 ms RTT apart on today's fiber, before the model emits a single token. Routing has to know the map.
Metro hubs are approximate; provider placement is illustrative of where open-weights inference clusters, not a claim about any one provider's exact facility. Distances are great-circle; the ~60 ms RTT is a real-world fiber estimate, not a Kottos measurement (cf. AWS N. California↔N. Virginia ≈ 58 ms). The straight-line speed-of-light floor is ~26 ms. Node color is static today: live demand coloring (green→amber→red from real measured load) ships with the hosted gateway's tape.