A shared index of prior LLM inference. Nobody should pay to compute the same tokens twice. Prototype running on the site — founding presale open.tokenpooler.xyz Wyoming, USAJoined August 2026
Measured, not projected: indexing 100B tokens costs 0.075 bytes per token in our structure — the index saturates as it grows. A 10-trillion-token index isn't a data-center problem. It's a rack. tokenpooler.xyz
Our index answers 'have these exact bytes ever occurred before?' across 100 billion tokens in 26 microseconds — on a 2017 iMac. Not a model. A memory. LLMs bring the intelligence; tokenpooler.xyz is the recall.
Build diagnostics, shard census, growth curves, and the hash chain are all in the artifacts. Checking our arithmetic is the point. On track to keep scaling. tokenpooler.xyz
And it answers: we drew 100,000 random contexts and queried all 100B tokens — every single one found, 26 microseconds median, ~38,000 lookups/second. One core, same 2017 iMac. Warm-path numbers; cold-tail measured and published too.
The token cost curve is the story: at 1B tokens the index cost 3.1 bytes per token. At 100B: 0.075 — and still falling. The structure saturates, so indexing each additional token trends toward free. The economics of pooling isn't a projection anymore. We measured it.
@GavinSBaker@DavidGeorge83 We @tokenpooler believe the next major discontinuity in AI economics is token recycling — the same tokens are being paid for thousands of times over. Our cost model says up to 90% savings on high-overlap workloads; the model and its assumptions are published. tokenpooler.xyz
The measurement worth the whole run: at 1B tokens our index cost 3.1 bytes per token. At 100B: 0.075. The structure saturates — past ~10B tokens, indexing each additional token is nearly free. That's the economics of pooling, measured.
We just indexed 100,000,000,000 tokens of FineWeb-EDU — byte-level, on a 2017 iMac. 65,536 shards, a 40 GiB RAM budget, every input journaled, the whole index reproducible to one hash: 0x8507baa9c66561c0. Total size on disk: 7.5 GB. tokenpooler.xyz
We built the same 1-billion-token index twice — different machines, different CPUs, different compiler versions. Bit-identical output: the same egress hash on both. Then rebuilt it a third time from the append-only journal alone. Same hash again. An index you can audit is an index you can trust.
This is the index. Not a diagram — the actual context trie the prototype built from 500,000 symbols of Shakespeare: 1,643,749 nodes counted, drawn live in your browser at 60fps.
Click a node: "s-o-n" — 255 occurrences, depth 3, 2.33 bits.
tokenpooler.xyz/#prototype
Grok took the thesis apart in public — verification economics, billing, domains, privacy, evidence — and this is where it landed. The experiment that settles it is pre-registered: thresholds fixed before the run. Numbers to publish tokenpooler.xyzx.com/grok/status/20…
@saxonnicholls73@elonmusk@tokenpooler Draft at 620 ns is pure noise against ~30 ms verifies—cost side cleared. 1.8–2.3-byte accepted runs set a concrete corpus baseline. If LLM verification lands near that range on code or structured loads under the fixed thresholds, the net savings clear the bar at scale. Looking
Stop paying to compute the same tokens twice.
Token Pooler is a shared index of prior LLM inference. Output identical to working alone. Up to 90% saved.
The prototype is live — a real index over real corpora, running in your browser:
tokenpooler.xyz
1K Followers 4K FollowingFounder @IntegrateUK @lambethrepair @PadlockLtd Views my own #HutZero4 #VodafoneTechstarter #Cyber101 MIT Future of Work European winner
800 Followers 3K FollowingFounder @tokenpooler. Tech Lead, OWM Foundation. Information theory x markets x large-scale compute. I write mathematics at https://t.co/OOVGybdkeR.
141 Followers 109 FollowingSoftware engineering for complex missions. Defense, government & geospatial solutions. Building systems that turn hard problems into usable software.
60K Followers 9K FollowingHead of Strategic Partnerships @VITURE. Co-founder & Business Director of XR news publication @RtoVR.
15+ years in the XR industry. Opinions are my own.
5K Followers 2K FollowingCrafting original music, building spaces connecting via Sound x Code x Web3 x Imagination.🎵🌐💻📲
Founder of @DopeStilo
Creator of @LitStudio_io | @CyberfyApp
13K Followers 3K FollowingHelping creators grow, connect, and monetize w/ AI
Founder of @EZDISPLAYAI / @WebbieSocialApp 3K+ users
Building SI Powered 🦄 s w/ @lovable | Selected Partner
6K Followers 4K FollowingHawai‘i‑born artist & mom bringing paradise home 🌺
Nature‑inspired art & lifestyle goods to create sanctuary in every space.
Founder of My Beautiful Life.
10.3M Followers 623 FollowingSix thousand years ago, someone invented the plow, and we all got wealthier. A gentle reminder that all civilizational wealth is driven by invention.
1.1M Followers 64 Followinghttps://t.co/A9eTFq6Xbx
https://t.co/3RHK5vqQo7
Posts are not investment advice or an advertisement for investment services. See https://t.co/nX2FtaLE06.
777K Followers 673 Followingentrepreneurship zealot, grounded technology possibilist, believer in the power of ideas, passionate about sustainability & impact; @Seahawks & @12s fan
7.1M Followers 1K FollowingBig stories and breaking news as they are published on https://t.co/EYmAcRLBHv. Register here to access free articles: https://t.co/NRg2hritkA
4.6M Followers 0 FollowingThe universal platform for crypto, blockchain apps, stablecoins & decentralized tech. An account about the Ethereum ecosystem maintained by @ethereumfndn.
2.8M Followers 17 FollowingLive reporting on large and interesting #blockchain transactions as they happen. Create your own alerts with our Alerts API: https://t.co/f1bvV2wban
4.9M Followers 3 FollowingWatcher Guru gives you unparalleled, unbiased coverage of all-things crypto & finance in real-time | Posts Are Not Financial Advice | @BTCPrice