Decentralised.ai
Decentralised Super Intelligence

Intelligence no single company controls.

An open network of AI providers, a router that picks one for you without reading your prompt, and memory that stays on your device. Anyone with a GPU can supply intelligence and earn PAI for it.

—Network, epoch —
—Provider nodes online
—Today's PAI reward pool
—Of every fee burned
—Common-knowledge price vs launch
Three roles, one network

Use it. Supply it. Own your context.

Today, one company holds the model, your conversations and the bill. Here each of those is held by a different party, and no single party can see or stop the whole.

01 · USE

Chat, or change one URL

Sign in with email or a wallet and chat. Developers keep the Anthropic, OpenAI or Gemini SDK they already use and point it at the network.

  • Crypto top-ups (opening soon)
  • Use your own vendor keys too
  • Console with keys, limits and usage
02 · SUPPLY

Put a GPU to work for the network

Run one container next to an open-weight model. The router sends it signed traffic, checks its answers with canaries, and credits PAI reward points for verified work (off-chain today, with no cash value).

  • Ollama, vLLM, llama.cpp, LM Studio
  • No static IP or port forwarding
  • Higher reasoning levels earn more
03 · OWN

Your memory stays with you

Conversations and preferences live in your browser or the dsi harness on your machine. Providers see one request at a time, without your account identity. Text you type is sent as written unless you route through Synapse, which strips what identifies you.

  • A different provider per session
  • No per-query inspection by the router
  • Little to leak: a provider holds one request, not your history
DSI Axon, the blind router

The cheapest provider that is good enough, chosen without reading your prompt.

The router sees the shape of a request — its length, the tools it needs, the reasoning level you ask for — never its meaning. It filters out every provider that can't handle the request, then balances cost, speed and quality among the rest.

If a provider disappears mid-answer, the stream continues on another one from the exact point it stopped. Your app sees one uninterrupted reply.

Architecture: the harness on the user's device holds memory; the router selects between vendor APIs and network nodes; the PAI ledger settles rewards.
Harness on your device → DSI Axon, the blind router → vendor APIs or network nodes → PAI ledger.

Reasoning levels

Every request is served at a level. Everyday answers are common knowledge and get cheaper every day. Frontier reasoning is scarce, so it needs a PAI stake. Stake is locked, not spent.

LevelWhat it doesKnowledgeRewardStake to use (staking not open yet)Nodes live
L0 · recallLookup, rewrite, classify (≤ 8B models)common×1none—
L1 · generalEveryday Q&A, summaries, code help (8–70B)common×2none—
L2 · reasoningMulti-step analysis, agents (70B+, reasoning models)novel×4from 1,000 PAI—
L3 · frontierFrontier-class and long-thinking modelsnovel×8from 10,000 PAI—
Privacy and continuity

No single company holds your conversation, so none can lose it, read it, or switch it off.

A centralised AI serviceDecentralised.ai
Where your history livesOn the vendor's serversOn your device; sent only with each request
Who sees who you areThe vendor, on every requestThe router strips identity; providers see an anonymous request
Who reads your prompts to route themThe vendorNo one; routing uses structure and your own hints
What one provider seesEverything, foreverOne session, then a different provider for the next
When the provider goes downYou waitThe reply continues on another provider mid-stream
Who can switch you offOne companyNo single operator; any node can serve

Honest limits: a provider serving a request can read that request, as with any hosted model. The network limits how much any one of them sees and removes your identity from it. Confidential-computing nodes and anonymous relays are on the roadmap.

PAI

A capped token whose supply follows real usage.

PAI pays the people who supply intelligence. 500M of it can only ever be created by doing verified work, and every fee paid in PAI burns some of it.

10BHard cap. 500M exists at launch and 500M is minted only for verified work. The 9B for investors and founders is minted in ten tranches, only as cumulative network fees pass $1M to $1B.
2 yrsEmission halves every two years, and falls further as the network grows.
30%Of every PAI fee is burned. Slashed stake is burned too.
70 / 20 / 10Daily rewards split between providers, verifiers and relays.
PAI supply projection: supply starts at the 500M genesis allocation, steps up by 900M as each investors-and-founders fee milestone is passed (nine of ten within ten years), and reaches about 8.7B; fee burn overtakes reward emission around year 2.7.
One adoption scenario, not a forecast: supply grows only as fee milestones unlock tranches, and burn exceeds emission from about year 2.7.

Common knowledge gets cheaper

As more operators serve L0–L1 models, the price of everyday answers falls every day. That's the live multiplier in the strip above.

Novel intelligence needs stake

L2 and L3 on the network require staked PAI, and the required stake rises with demand. That rations scarce reasoning by commitment, not by who you are. Your own vendor keys are never stake-gated.

Operators put skin in the game

Higher-level providers post a bond. Serving a cheaper model than declared costs half of it.

PAI currently runs on an off-chain ledger. The reference contract is unaudited and not deployed, and no token generation event is scheduled. Nothing on this page is an offer of securities or a promise of earnings; figures in the whitepaper are illustrative.

Supply intelligence

Three commands from GPU to paid node.

Docker Compose starts an open model server, a Cloudflare tunnel and dsi-node. The node registers its models, accepts only router-signed requests and heartbeats every 30 seconds. Rewards settle daily.

# Ollama + tunnel + dsi-node
curl -fsSLO https://decentralised.ai/dl/docker-compose.yml
# any open-weight model your hardware fits (see /node)
DSI_API_KEY=ds_live_... DSI_MODEL=qwen2.5:7b docker compose up -d

# already running vLLM / llama.cpp / LM Studio?
LLM_BASE_URL=http://localhost:8000/v1 node dsi-node.mjs up
node dsi-node.mjs earnings
Build

Your SDK already works.

Drop-in Anthropic, OpenAI and Gemini APIs with streaming, tools, vision, files and batches, plus an MCP server. Use model: "auto" to let the router choose, or name a model to pin it.

from anthropic import Anthropic

client = Anthropic(
    api_key="ds_live_...",
    base_url="https://api.decentralised.ai/anthropic",
)
msg = client.messages.create(
    model="auto", max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

Intelligence should be a public utility, not a private possession.

Start with a conversation, a line of code, or a spare GPU.