Gateway Setup Options

Choose your gateway setup type - go-livepeer binary, SDK implementation, managed platform, or hosted service - and operational mode.

Gateway operators make three independent choices when deploying a Gateway: setup type (what software to run), operational mode (on-chain or off-chain), and node type (what workloads to route).

Setup type: The software you run.

• Livepeer Protocol go-livepeer (Docker or source deployment) which is the core implementation for Gateway nodes
• SDK/Custom (Python, browser, mobile) which provide custom language abstractions for the Livepeer Protcol
• DevOps Managed Platforms (eg. GWID) which abstract the Deployment Operations and provide a ‘one-click deploy’ experience.
• Hosted (Livepeer Studio, Cloud SPE) which provide Gateway application layer services (not a gateway deployment)

Operational mode: How your gateway integrates with the Livepeer protocol.

• Off-chain uses a remote signer for payments and manual orchestrator discovery.
• On-chain connects directly to the Livepeer Network on Arbitrum for payments and automatic pooled orchestrator discovery.

Node type: What workloads your gateway routes.

• Video (RTMP transcoding)
• AI (Inference & real-time AI routing)
• Dual (both pieplines on a single node)

Setup Types

go-livepeer

The standard gateway binary. Covers all node types - Video transcoding, AI inference, and Dual (both) - and supports both operational modes.

Install options: Docker (recommended) or build from source.

Operational mode is an independent choice:

Node type is also an independent choice:

• Video - RTMP transcoding to HLS. Replaces cloud services (Mux, AWS MediaLive, Wowza).
• AI - inference routing (text-to-image, image-to-video, LLM, audio-to-text, and more).
• Dual - both video and AI on a single node. Linux only for the AI component.

Correcting a common misconception: Older docs and community guides state that running an off-chain gateway requires your own orchestrator node (and therefore a GPU). This is incorrect. Gateways route to orchestrators on the network. You do not need a GPU.

Quickstart

From zero to a running gateway with a test request.

Requirements

Hardware, OS, network, and operational mode requirements.

SDK / Custom

Build a Livepeer gateway client in Python, browser, mobile, or embedded systems - without shipping the Go binary. The remote signer architecture handles all Ethereum payment operations; your implementation handles media routing.

Reference implementation: livepeer-python-gateway by j0sh - github.com/j0sh/livepeer-python-gateway

Workload support:

• Live AI (live-video-to-video) - fully supported; remote signer designed for this first
• BYOC (Bring Your Own Compute) - supported; uses HTTP not gRPC for discovery
• Batch AI - same payment mechanism; full remote signer support not confirmed as shipped
• Video transcoding - excluded by design (ticket signing is synchronous in hot path)

Remote Signers

How the remote signing protocol works.

Requirements

Hardware and off-chain requirements.

Managed Platform

Other DevOps Platforms like Stream.Place may also meet your needs

SPE Funded Experimental

GWID (Gateway Wizard) is a fully managed DevOps platform for Livepeer. Single-click deployment with integrated playback testing.

GWID and other ecosystem projects are not maintained by Livepeer. Consider this experimental.

GWID Github (VideoDAC)

View the GWID repository on GitHub

GWID updates:

• GWID SPE Proposal: Gateway Wizard Phase 1
• Get to know GWID - A Fully Managed DevOp Platform for Livepeer

Hosted Gateway

Use an existing gateway operator instead of running your own. You pay their service rate; they handle all infrastructure, payments, and orchestrator management.

This is the right choice if you are building an application and do not need control over compute routing, orchestrator selection, or pricing.

Hosted gateway providers:

• Livepeer Studio - video API for developers; per-minute pricing. livepeer.studio
• Livepeer Cloud - free public AI and video gateways (SPE-funded). livepeer.cloud
• Daydream - commercial AI video product with embedded gateway

Gateway Providers

Compare hosted gateway providers and their capabilities.

Next Steps

Requirements

Hardware, OS, network, and operational mode requirements for all gateway types.

Install

Docker, Linux binary, and community install methods.

Quickstart

From zero to a running gateway with a test request.