←
Nate Clancy465 posts
Nate Clancy avatar

Nate Clancy

@Nate_Architect

Co-Founder and Chief Business Officer at Architect. Building compute markets. UChicago MBA (derogatory), Biotech Bro, Midd Kid

◷ Joined September 2019▧ 54 Photos and videos
Nate Clancy avatar
Nate Clancy@Nate_Architect·Oct 7

Say it once more for the folks in the back: compute is a commodity. Nobody buys oil or electricity on a monthly subscription. Free yourself from the SaaS paradigm of bundled services and high margins. There's a better way, and it's Liquid Inference. Check it out, first 500 get $20 in free tokens liquidinference.ai/. Leverage the power of market competition for the best possible pricing. Purchase only what's needed. Substitute models and switch suppliers to control costs. Buyers pay the lowest quote per prompt across any subset of over 700 models. Providers can sell spare GPU capacity and create a new sales channel.

Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost tokens. Providers onboard in minutes, not weeks. Buyers have full price visibility and receive 20% of referred fees in free inference. More info: Liquid Inference can be used in place of any OpenAI or Anthropic API-compatible backend. Behind it, our team has leveraged our experience trading and building financial exchanges to create real-time two-sided price discovery for inference. Benefits for buyers and providers: INFERENCE BUYERS • Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more. Full multi-modal support. • Hundreds of open- and closed-weight models. Create routing rule presets or use our Auto routing algorithms. • Providers compete dynamically on price for every prompt, offering the lowest marginal cost. • Sign up for free with email, first 500 users get $20 of free inference. • Receive 20% of referred fees as free inference, 10% for second-level referrals. INFERENCE PROVIDERS • Onboard through the Liquid Inference app. We verify new providers in minutes, not weeks. • All prompts are OpenAI API standard. Simple REST/Websocket API to register models and quotes. • Update quotes dynamically based on your own costs. Monetize GPU capacity only when you want. • Standardize payouts via Stripe, full itemized records of all jobs performed.

0:44
Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 16

Architect’s pace and a sense of urgency can cause culture shock to the uninitiated. We ship products so fast that we woke up one day and realized we needed to present a more united front from a brand perspective. We have many products but at a high level they amount to the same goal: building markets to serve the dynamic and multifaceted needs of the AI industry. From GPU capacity, to inference, to derivatives, we’re the entry point to frontier markets. And this is the tip of the iceberg.

Architect is taking account of what our company has grown into this year. We have a new mandate and a new website. Dynamic inference markets, GPU capacity trades, OTC compute derivatives, US futures, developer tools, data aggregation, and more to come very soon.

0:12
Brett Harrison avatar
⟳ Nate Clancy retweeted
Brett Harrison@BrettHarrison·Nov 12

We've steadily improved our Liquid Inference routing algorithm to optimize for cache hit-rate. We've achieved >90% average across models, often realizing higher rates with DeepSeek and GLM providers.

Post attachment
Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 12

Trust but verify is the correct policy for most things in life.

Liquid Inference checks every tool call a provider returns. Bad call on a non-streamed request? We drop it and send the job to the next offer. Provider returns nothing? You pay nothing. Last 7 days: 99.64% of tool-call answers had no bad call. liquidinference.ai/docs/erro…

Post attachment
Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 11

The enterprise playbook won't do much to control costs. Only the expensive products will respond to RFPs. It's not flexible enough for the current market. Liquid Inference is the jack-of-all trades for AI procurement. The top providers are constantly juggling their unused compute. They'll be serving one month and then fully booked with dedicated contracts the next. It's like herding cats. What they should do is run tests with a tight budget to see where you can substitute to cheaper models. Then hit up our entire provider network for a quote based on your specs. We'll herd the cats and fill in all the blanks.

Reserve capacity on Liquid Inference. Pick a model (text, video, image or speech) and set your terms: a monthly pool, rate limits, uptime, region and a term of up to 12 months. You get a quote, and you can negotiate before you accept. Fixed monthly fee. Zero data retention on every reservation. inference.ai.exchange/docs/r…

0:27
Brett Harrison avatar
⟳ Nate Clancy retweeted
Brett Harrison@BrettHarrison·Nov 11

Mean reversion in the GPU rental market. Over the past month, 1-year US GPU rental rates for A100, H100, and H200 have reverted back to mid-October levels, while B300 has given back most of its late-October gains. What we think is driving the divergence: - Neocloud credit pressure. With neocloud equities down sharply and borrowing costs rising, some operators are moving B300 capacity at a discount to raise cash. - Inference is driving demand. Neocloud demand continues to shift from training to inference (Bloomberg, below). Better small-to-mid-size open-weight models make older Nvidia accelerators more economical for many common inference workloads. - B300 supply is catching up. B300s are the most commonly requested chip in the OTC market, and availability has historically been scarce. But we now see a number of B300/GB300 clusters coming online between end of Q4 2026 and mid Q1 2027. We're brokering spot and options trades across the accelerator spectrum — reach out if interested.

Post attachment
Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 5

To whom it may concern: less liquid glass, more liquid inference. OSS models will continue to capture share, esp with the the release of Kimi K3.1, Tencent Hy4. Apple should run a dollar for dollar test to see which model can get CarPlay to respect alternative sorting methods of Spotify playlists. Niche bug, but I'd be so grateful.

Apple, $AAPL, has cut internal AI budgets to rein in spending, per Bloomberg Some engineers’ daily AI usage cap was lowered to $200, from $300. It follows similar moves at Microsoft and McKinsey, which have limited employees’ AI use as costs pile up.

Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 5

AI infra credit crunch, CFTC comment period on compute derivs, GPU rental prices up, inference tokens down. Now a blue wave that threatens to slow the build out. I can feel the space tighten between the rock and a hard place. We need the compute spark spread.

Nate Clancy avatar
Nate Clancy@Nate_Architect·Nov 3

Hit us up if you’re gonna be at FIA Expo this year.

Superintelligence markets will begin in Chicago due to DRW, Jump, CME, Architect, and hundreds of CFTC-regulated industry partners working to financialize compute and inference in the US. If you’re at FIA come visit Architect’s office, trade B300s, and play our CTO in 301.

Post attachment
Nate Clancy avatar
Nate Clancy@Nate_Architect·Oct 26

How it feels when you switch to Liquid Inference.

0:15

Why has nobody made an *actually* open router? Feel like such an opportunity to have lower cost

Nate Clancy avatar
Nate Clancy@Nate_Architect·Oct 23

I'm particularly excited about reservations. If we can build meaningful liquidity in short to medium term reserved capacity deals, we could save a lot of friction. Over time, I imagine most will have a hybrid approach with a base of reserved capacity for higher consequence tasks, and purchase any overflow that's more elastic transactionally. For both markets, providers will compete and you can compare on Liquid Inference.

Announcing Reservations on Liquid Inference. Inference buyers can now reserve batches of tokens in advance at fixed prices over any time period. Providers compete to offer the best terms and SLAs instantly. How it works: • Enter a lock-in duration from 1 to 12 months • Specify token rate and uptime requirements • Select from ZDR, SOC2, and other compliance/privacy features • Receive multiple quotes and terms • Negotiate through in-app messaging directly with providers • Optionally allow overage to automatically query the spot market Providers benefit from standardized contracts, automated billing, SLA monitoring, and zero additional fees to participate. Check it out and let us know, we’re here for all feedback.

0:44
Doruk İşmen avatar
⟳ Nate Clancy retweeted
Doruk İşmen@dorukismen·Oct 22

.@SinaAfra bir konuşmasında AI/inference tokenlarını toplu almanın ve ticaretini yapmanın gelecekte önemli bir yer tutacağından bahsetmişti. Architect olarak bu geleceği liquidinference.ai üzerinden hayata geçirdiğimizi duyurmaktan mutluluk duyuyorum: - 1-12 ay arası sabit fiyatla token rezervasyonu - Sağlayıcılar en iyi fiyat ve SLA için yarışıyor - ZDR, SOC2 gibi gizlilik ve uyumluluk seçenekleri - Sağlayıcılarla uygulama içinden doğrudan pazarlık - Kapasite aşılırsa spot piyasaya otomatik geçiş

Announcing Reservations on Liquid Inference. Inference buyers can now reserve batches of tokens in advance at fixed prices over any time period. Providers compete to offer the best terms and SLAs instantly. How it works: • Enter a lock-in duration from 1 to 12 months • Specify token rate and uptime requirements • Select from ZDR, SOC2, and other compliance/privacy features • Receive multiple quotes and terms • Negotiate through in-app messaging directly with providers • Optionally allow overage to automatically query the spot market Providers benefit from standardized contracts, automated billing, SLA monitoring, and zero additional fees to participate. Check it out and let us know, we’re here for all feedback.

0:44
Nate Clancy avatar
Nate Clancy@Nate_Architect·Oct 22

Good news everybody, we’re going back on the gold standard.

Last month, we demonstrated high-rate alchemy: turning mercury into real, stable gold, beating CERN’s record by a factor of 10. Last week, we enriched isotopes in the world’s most powerful plasma centrifuge, beating the Soviet record that stood for 40 years. Now, we’re building a fusion reactor in San Francisco to achieve record power density.

1:44