Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.livepeer.org/llms.txt

Use this file to discover all available pages before exploring further.

Most developer tasks (calling AI pipelines, uploading assets, testing playback) require only an API key or a gateway endpoint. A full local Livepeer stack is necessary when developing node software, testing custom BYOC containers against a real orchestrator, or working through payment flows without spending real ETH.

​
Choosing a Development Path

​
Community Gateway (No Setup)

The public community gateway at https://dream-gateway.livepeer.cloud accepts unauthenticated AI inference requests for development. It routes requests to active mainnet orchestrators; no account or deposit is required. 
curl -X POST "https://dream-gateway.livepeer.cloud/text-to-image" \
  -H "Content-Type: application/json" \
  -d '{"model_id": "ByteDance/SDXL-Lightning", "prompt": "a blue house"}'
This is appropriate for prototyping and initial integration testing. For sustained development load, run a local gateway to avoid rate limiting.

​
Installing go-livepeer

Download a pre-built binary from the go-livepeer releases page: 
# Linux x86-64 (replace RELEASE_VERSION with the latest release tag)
wget https://github.com/livepeer/go-livepeer/releases/download/<RELEASE_VERSION>/livepeer-linux-amd64.tar.gz
tar -zxvf livepeer-linux-amd64.tar.gz
mv livepeer-linux-amd64/* /usr/local/bin/

# GPU-accelerated build (NVIDIA)
wget https://github.com/livepeer/go-livepeer/releases/download/<RELEASE_VERSION>/livepeer-linux-gpu-amd64.tar.gz
tar -zxvf livepeer-linux-gpu-amd64.tar.gz
mv livepeer-linux-gpu-amd64/* /usr/local/bin/
macOS (Apple Silicon): 
wget https://github.com/livepeer/go-livepeer/releases/download/<RELEASE_VERSION>/livepeer-darwin-arm64.tar.gz
tar -zxvf livepeer-darwin-arm64.tar.gz
mv livepeer-darwin-arm64/* /usr/local/bin/
After installation, verify with livepeer --version and livepeer_cli --version. Most developers start with the community gateway and never need local infrastructure. If you do need it, local gateway is the next step.

Local Gateway

Running a go-livepeer broadcaster node locally connected to mainnet.

Local Orchestrator

Running a local orchestrator for testing BYOC containers and payment flows.

Tooling and Metrics

Prometheus metrics and the livepeer/monitor container for local node observation.
Last modified on May 19, 2026