# Batch and live inference need different interruption terms Markdown copy of https://realalpha.app/s/batch-and-live-inference-need-different-interruption-terms/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy. - Speaker: [Evan Conrad](https://realalpha.app/people/evan-conrad/) · SF Compute - Host: [Shawn Wang (swyx)](https://realalpha.app/people/swyx/) · Co-founder, AI Engineer · Wrote “The Rise of the AI Engineer” and founded Smol AI, maker of AI News. - Show: Latent Space - Episode: [The Programmable Data Center — Evan Conrad, SF Compute](https://realalpha.app/v/EAtLq9_vrE0/), Oct 20, 2026 - Moment: 14:13 to 19:35 of the episode (5 min), playing on https://realalpha.app/s/batch-and-live-inference-need-different-interruption-terms/; the episode from there: https://realalpha.app/v/EAtLq9_vrE0/?t=853 ## Quote > “if I have live inference customers who are expecting me to be online, then you can interrupt me, but **in a month, maybe two months**, maybe three months.” > — [Evan Conrad](https://realalpha.app/people/evan-conrad/) at [16:35](https://realalpha.app/v/EAtLq9_vrE0/?t=995) · Latent Space ## Takeaways 1. Batch workloads can tolerate much shorter interruption notice. 2. Live inference may need months to adapt to a capacity change. 3. Near-term unsold compute can fall in price as it approaches. ## About this segment Evan Conrad contrasts short-notice interruptions for batch workloads with longer notice for live inference, then describes how compute prices change over time. Contract terms need to reflect each workload’s flexibility. From “The Programmable Data Center — Evan Conrad, SF Compute”, Oct 20, 2026. [Watch the full episode](https://realalpha.app/v/EAtLq9_vrE0/) ## Transcript Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there. [14:20](https://realalpha.app/v/EAtLq9_vrE0/?t=860) overall like i just want to like i want people to understand the shape of this market um you mentioned like preemption you know and and you know we talked about spot instances and how that the analogy is yeah and then there's also you know booking a month out how far out do this do these markets go and is is real time or sort of preemption more interesting to you versus uh far being further further out um to answer your first question um three to five years um wow we're And like month by month or quarter by quarter or how's this? [14:51](https://realalpha.app/v/EAtLq9_vrE0/?t=891) Are you asking how the cash flow works? The contracts, like the futures contracts, right? Again, I'm a former contracts derivatives trader. In the market itself, like is in the broader market, clusters are financed three to five years. So the payments are for over that period of time. There is also like blocks of capacity in our order book, which can extend any arbitrary time. There's some stuff that we have to do for the cash flow on that. [15:18](https://realalpha.app/v/EAtLq9_vrE0/?t=918) Right now what we do is we just ask people to pay entirely up front for a block. We don't ask them to do that for a lease for a longer term contract. This gets into something that I definitely need a whiteboard to explain. But you had another question I was about to answer. Do you want real time? What's more interesting to you, real time or longer out? So we care more about longer out because we're trying to build a forwards curve that has a lot of liquidity on it. [15:46](https://realalpha.app/v/EAtLq9_vrE0/?t=946) the, these are kind of the same thing and kind of not. So what we do is we can say, you can buy an hour out. You can buy right now to the next hour, or you can buy right now to. the next three years and anywhere in between that's wild i know um and so the um you know or five years technically um the there's a certain difference that happens that's dependent for each customer basically like if i have a workload that is um uh that's batch inference basically where i can be interrupted at any point i don't really care um then my ability to be cut off is probably like, I need an hour of time to know that I'm going to be cut off and then I'm good. Or I can even be notified in, you know, a minute or two. But if I have live inference customers who are expecting me to be online, then you can interrupt me, but in a month, [16:50](https://realalpha.app/v/EAtLq9_vrE0/?t=1010) maybe two months, maybe three months. And then I can adapt to that capacity over that period of time. But you cannot interrupt me in a minute. And so those two things are priced differently. And the reason why they're priced differently is because what is the price you would pay in order to interrupt your batch job? It's very different than the price you would pay to interrupt your live job. If you have a live job, you are probably paying an SLA when you break for your customer. Does that make sense? Yeah, I see. So this is actually the market for breaking leases. [17:22](https://realalpha.app/v/EAtLq9_vrE0/?t=1042) These are the market for breaking leases, basically. Oh, my God. And then there's also the market for future leases, or like for leases that are... Oh, I thought this was like a subletting situation. This is like... Oh, the lease break. So one way to think about it is in power markets, there's actually two markets. There's like the day ahead market and there's the live market. Compute kind of has the same thing, where it has capacity that is coming online, or capacity that's about to arrive to you, and then capacity that is currently in use. [17:52](https://realalpha.app/v/EAtLq9_vrE0/?t=1072) And these have different price dynamics. Okay. Interesting. Backwardation or contango? Backwardation or contango? So is compute further out price higher than spot or lower than spot? Is compute further out price? Does it go like this? Does it go like that over, you know, over like one year out, two year out? Do? Oh, this is both at different times. I find it fascinating that you don't know. Yeah. I mean, both. [18:21](https://realalpha.app/v/EAtLq9_vrE0/?t=1101) It depends on who you are. Okay. So I'll make the case – wait, so you're asking, is compute sold right now? So compute like the same unit of compute today, maybe not today, maybe a month out versus one year out versus two year out. Is that curve going up or going down? We see like a hump. Oh, my God. Okay. Explain. Like I think this will make intuitive sense. It's basically like if I have milk and it is about to expire, I will lower the price on it. [18:48](https://realalpha.app/v/EAtLq9_vrE0/?t=1128) Yes. And so that's basically what we see. So it's the NVIDIA release cycle, basically, right? Well, we're more saying, like, if there's a block of compute and it's approaching now, it can't be sold in the past. And so it has to drop its price in order to clear at some price. And so initially you see this, like, drop where stuff that's sold right now, anything that's on the market right now, is something that hasn't been sold. [19:11](https://realalpha.app/v/EAtLq9_vrE0/?t=1151) And so therefore the price will drop. And then it goes up to where it wants to be. And then maybe compute in the future is worth less because people don't want – like people would like the compute now. And so they're sort of paying for the shorter lead time. And they pay less for the compute that's off into the future. This is what I think a normal healthy curve looks like.