Put your GPU to work on Livepeer. Join a pool or run your own node.

Service payouts24h
$603.9
Protocol rewards24h
$5.6K
Orchestrator docs

Choose the right path

Do not buy tokens or new hardware before deciding which role you actually want to run.

Fastest path

Join a pool

Connect as a worker behind an existing Orchestrator. The operator handles registration, LPT, routing, and payouts; you provide GPU compute and receive off-chain earnings under the pool’s terms.

  • NVIDIA GPU and Linux
  • Docker or go-livepeer
  • Verified payout terms
No LPT requiredPool setup guide

Best with 24 GB+ VRAM

Run AI-first

Serve inference workloads where capability, price, latency, and uptime matter more than active-set stake.

  • CUDA 12+
  • Docker
  • NVIDIA Container Toolkit
Lower stake barrierAI operations

Full operator path

Run a solo node

Operate go-livepeer, publish your service address, manage the wallet, set prices, and monitor rewards.

  • Arbitrum ETH
  • LPT for video
  • Public service URI
Most responsibilitySolo setup guide

Baseline requirements

These are the practical requirements that apply before protocol configuration.

Supported GPU

NVIDIA is the supported hardware-accelerated path. Confirm the host can see the card with nvidia-smi.

Production host

Use Linux for production GPU workloads. AI also needs Docker, CUDA 12+, and NVIDIA Container Toolkit.

Public network

Use stable, low-latency internet. Solo nodes need a public domain or static IP and an open service port.

Operating budget

Account for electricity, storage, bandwidth, and maintenance. Work and earnings are not guaranteed.

Arbitrum

Arbitrum One

Solo on-chain nodes need ETH on Arbitrum One for activation, reward calls, ticket redemption, and ongoing gas.

Official Arbitrum Bridge

$LPT stake

Solo video operators need enough self-stake and delegated LPT to enter the active orchestrator set. Pool workers do not manage stake.

View active orchestrators