Live on Robinhood L2 · 14,832 GPU + NPU nodes online
The engine of the on-chain intelligence economy

Rent The Supercomputer

A Robinhood L2-native compute layer that turns idle GPU & NPU capacity into a permissionless supercomputer for the AI age. Run inference, train models, deploy autonomous agents — settled trustlessly in USDC on Robinhood L2.

Browse marketplace →
Compute online
2,418PFLOPs
Active providers
14,832
Jobs settled (30d)
1.2M
Paid to nodes
$48.7M USDC

Spin up compute in under nine seconds.

14,832 verified GPU & NPU nodes, settled trustlessly on Robinhood L2, slashing-bonded against downtime. No gatekeepers, no waitlists, no hyperscaler markup — filter by accelerator class, region or framework.

Every job, on-chain & visible.

Job intents, agent transactions, payment streams and slashings stream live from Robinhood L2. Every output cryptographically attributable — verify any settlement on Robinscan.

~/vortano/network.log — robinhood-l2/mainnet LIVE
Jobs in flight
3,418
↑ 12.4% · last 24h
Network throughput
jobs / min
USDC streamed today
$184,720
across 947 active rentals

A full-stack AI model suite.

Text, images, autonomous agents and an AI-native OS — every model runs on decentralized compute and every output is cryptographically attributable on Robinhood L2.

TXT

Text generation

High-throughput LLMs — instruction-tuned, 128k ctx, streaming.

H100 ×2 from $3.20/hr
IMG

Image synthesis

State-of-the-art 1024² generation, LoRA-ready, 12s/batch.

RTX 4090 from $0.41/hr
AGT

Autonomous agents

On-chain agents that transact, coordinate & self-execute on Robinhood L2.

A100 80G from $1.42/hr
OS

AI-native OS

One runtime orchestrating every model, agent & inference job.

L40S from $0.92/hr

The cockpit for the on-chain AI economy.

A live, in-browser command interface to the network via the voltra CLI. Spin up models, deploy agents, run inference and stream payments — all from a single pane of glass.

~/vortano · zsh — vortano-cli v0.4.2 SANDBOX
▮ Vortano CLI v0.4.2 — connected to robinhood-l2-mainnet · block 18,492,113
Type help for commands. ↑/↓ navigates history. Try ls gpu or deploy llama-3.
vortano@robinhood-l2:~$
Quick commands
Install on your machine
curl vortano.org | sh

macOS · Linux · WSL2. Auto-detects your wallet via EIP-6963. No daemon — single 4.2MB binary.

5–10× cheaper than the hyperscalers.

Our hybrid NPU + GPU router sends ultra-efficient edge inference to NPUs and heavy training to GPUs, load-balancing to slash cost-per-token to industry-leading lows. No rack rental, no markup, no quarterly board — you pay the silicon, not the suit.

Accelerator
Vortano market
AWS
Google Cloud
Azure
H100 80GB SXM5
$2.18 /hr
$12.29 /hr
$11.06 /hr
$10.96 /hr
A100 80GB PCIe
$1.42 /hr
$5.12 /hr
$4.32 /hr
$4.96 /hr
TPU v5p 1×chip
$3.42 /hr
$8.95 /hr
L40S 48GB PCIe
$0.92 /hr
$3.78 /hr
$3.21 /hr
$3.42 /hr
RTX 4090 24GB
$0.41 /hr

benchmark refreshed every 4h · on-demand list pricing · region-normalised to us-east

Trustless compute, in three movements.

Verifiable inference via fraud proofs. Every output cryptographically attributable. Settlement on Robinhood L2, reputation written to a public registry.

I

Connect & deposit

Bring any EVM wallet. Deposit USDC, ETH or VRTN into the rental escrow. No KYC for jobs under 10k USDC.

II

Pick an accelerator

Filter nodes by class, memory, region, framework. Every provider posts a slashing bond — bad nodes get burned.

III

Stream payments

Pay per second from escrow. Pause, resume or fail-over to a hot replica. Receipts settle automatically on Robinhood L2.

Got idle silicon? Make it earn.

Monetize idle GPU & NPU capacity on the Vortano mesh — anything from a single 4090 to a 64-node H100 cluster. Set your floor price, post a bond in VRTN, and start streaming USDC.

Earn from $620 per H100, per month — passive.

Estimated revenue based on the trailing-30-day median rental price and 78% network utilization. Payouts settle every block to your wallet.

2 × H100 SXM5
Median rate$2.18 /hr
Assumed utilization78%
Protocol fee2.5%
Est. monthly revenue$2,449 USDC

Onboard in four steps.

No KYC for nodes under 100 TFLOPs aggregate. Slashing-bonded providers run the network.

  1. 1

    Install the agent

    curl vortano.org/agent | sh — runs in a container, isolated from your host.

  2. 2

    Post a bond in VRTN

    ~$200 worth of VRTN per accelerator. Recovered when you exit the network gracefully.

  3. 3

    Set your floor price

    The market discovers price — you set a refusal threshold below which jobs aren't accepted.

  4. 4

    Stream revenue

    USDC streamed to your wallet every block via Superfluid. Withdraw any time.

$VRTN — the compute credit of the network.

Stake to provide GPU & NPU nodes. Pay-as-you-go for inference, training and agents. Vote on slashing rules. Launching on Robinhood L2 mainnet via a fair-launch LBP.

VRTN

Vortano Token

ERC-20 · Robinhood L2 · 18 decimals

$VRTN settles every job, bonds every provider and governs every protocol parameter. Holders earn a slice of each rental in real-time, streamed via Superfluid on Robinhood L2.

Total supply1.0 B VRTN
Initial FDV$42 M
LaunchJun 18 2026

Token distribution

Node providers
38%
Public sale
22%
DAO treasury
18%
Core contributors
14%
Liquidity & LPs
8%

Launching on Robinhood L2 mainnet · audited by Spearbit

Where the protocol is going.

Major milestones are gated by DAO vote post-launch. Dates are targets, not promises.

Q1 · 2025 · Shipped

Genesis

  • Whitepaper v1
  • Testnet on Robinhood L2 Sepolia
  • First 100 providers
  • Seed round closed
Q4 · 2025 · Shipped

Mainnet

  • Mainnet on Robinhood L2
  • GPU marketplace live
  • Spearbit audit
  • $8M TVL bonded
Q2 · 2026 · In progress

Expansion

  • Hybrid NPU + GPU router
  • AI model suite (text + image)
  • $VRTN token launch (LBP)
  • Live shell terminal
Q4 · 2026 · Planned

Sovereignty

  • Autonomous on-chain agents
  • AI-native OS
  • zk-fraud proofs for inference
  • DAO governance v1

Frequently asked questions.

A Robinhood L2-native compute layer that turns idle GPU & NPU capacity into a permissionless supercomputer for the AI age. Providers monetize their hardware while developers tap inference, training and autonomous agents — all settled trustlessly in USDC on Robinhood L2, with each provider posting a VRTN bond that gets slashed for misbehavior.
Every rental intent, agent transaction, payment stream and provider claim is recorded on Robinhood L2 mainnet, and every output is cryptographically attributable. Inference itself runs off-chain on provider hardware, but optional (zk) fraud proofs are available for jobs that need full verification.
Our hybrid routing engine sends ultra-efficient edge inference to NPUs and heavy training to GPUs, with load-balancing that pushes cost-per-token to industry-leading lows. No data-center markup, no corporate margin — price is discovered by an order book, not a board meeting.
USDC is the default. You can also pay with ETH or VRTN via auto-swap. Providers receive USDC streamed directly from escrow to their wallet via Superfluid.
Three things: (1) provider bond — slashed for misbehavior, (2) governance — voting on protocol parameters, and (3) revenue share — stakers earn a slice of protocol fees.
Not for jobs under 10,000 USDC. Providers under 100 TFLOPs aggregate are also KYC-free. Above that, we integrate with zk-KYC providers for optional compliance.
▮ Mainnet · Robinhood L2

The compute is decentralized.
The terminal is live.

This isn't a roadmap — it's the engine of the on-chain intelligence economy, and it's already running. Connect a wallet and ship.

Read the litepaper