} ; }; the go-livepeer flags needed to run as an Orchestrator. By the end, a working startup command is ready and each flag is understood. **Prerequisites:** * go-livepeer installed and GPU detected. See . * Arbitrum wallet with ETH for gas. See . * The hardware session limit number from the `livepeer_bench` test in . ## Essential Flags These flags must be set every time go-livepeer starts as an Orchestrator. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -network arbitrum-one-mainnet ``` Tells go-livepeer which network to connect to. The default is `offchain` - without this flag the node does not participate in the Livepeer Protocol at all. **Options:** * `arbitrum-one-mainnet` - production network * `offchain` - local or dev only, no on-chain participation ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -ethUrl ``` Points go-livepeer at an Arbitrum One RPC endpoint to read and write on-chain state - Orchestrator registration, reward calls, ticket redemption. ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -ethUrl https://arb-mainnet.g.alchemy.com/v2/YOUR_API_KEY ``` This must be an **Arbitrum One** endpoint, not an Ethereum L1 endpoint. See for how to set up a reliable RPC. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -ethAcctAddr ``` Specifies which ETH account acts as the Orchestrator identity on the network. This account holds staked LPT, receives ETH fee payments, and signs on-chain transactions. If omitted, go-livepeer creates a new account and prompts for a passphrase to encrypt the keystore. The key is stored at `~/.lpData/arbitrum-one-mainnet/keystore` by default. The private key controls the wallet and all funds on it. Back it up securely before proceeding. A lost keystore cannot be recovered. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -orchestrator -transcoder ``` `-orchestrator` enables the on-chain protocol role - the node participates in job routing, makes reward calls, and is visible to Gateways. `-transcoder` enables local GPU transcoding - the node processes jobs using its GPU. Use both together for the standard combined setup where one machine handles all roles. For alternate configurations: Mode Flags Use when **Combined** (most common) `-orchestrator -transcoder` One machine handles all roles **Orchestrator-only** `-orchestrator` Remote Transcoder workers are connected via `-orchSecret` **Transcoder-only** `-transcoder -orchAddr ` Contributing GPU to another Orchestrator's pool See for the O-T split and Siphon configurations. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -nvidia ``` Specifies which NVIDIA GPUs go-livepeer uses for transcoding. Omitting this flag falls back to CPU transcoding, which is significantly slower and not competitive on the network. ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -nvidia 0 # Single GPU - device ID 0 -nvidia 0,1 # Two GPUs -nvidia all # All available GPUs ``` Check GPU IDs before starting: ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} nvidia-smi -L ``` For AI-only operation (no video transcoding), `-transcoder` is not required but `-nvidia` is still needed to expose the GPU to AI Runner containers. See [Adding AI inference](#adding-ai-inference) below. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -maxSessions ``` Sets the maximum concurrent transcoding sessions the node accepts. The default is 10. Set it to the **minimum of the hardware limit and the bandwidth limit**. **Hardware limit:** the last session count from the `livepeer_bench` test in where Real-Time Duration Ratio was ≤ 0.8. **Bandwidth limit:** available symmetric bandwidth (Mbps) ÷ 6 Mbps per stream × 0.8 margin. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} session limit = min(hardware limit, bandwidth limit) ``` Example: hardware limit 12, bandwidth 100 Mbps → bandwidth limit \~13 → use `-maxSessions 12`. `-maxSessions` applies to video transcoding only. AI inference capacity is controlled per pipeline by the `capacity` field in `aiModels.json`. See [Adding AI inference](#adding-ai-inference) below. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -pricePerUnit ``` Sets the price charged per unit of transcoding work. The unit is **wei per pixel**, not ETH. * 1 ETH = 1,000,000,000,000,000,000 wei * A typical starting price is **500-2,000 wei per pixel** * Check current market rates at [tools.Livepeer.cloud](https://tools.livepeer.cloud/ai/network-capabilities) Setting this in ETH rather than wei results in a price orders of magnitude below market rate. Setting it too high means Gateways route jobs to lower-priced Orchestrators instead. ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -pricePerUnit 1000 ``` `-pricePerUnit` sets the startup price. The on-chain registered price used for discovery is set separately during activation via `livepeer_cli`. Both can be adjusted independently later. ```text icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -serviceAddr : ``` Declares the public address at which Gateways reach the Orchestrator. This is stored on-chain during activation and is how the network discovers the node. ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -serviceAddr 203.0.113.42:8935 # or with a domain name (preferred): -serviceAddr orch.yourdomain.com:8935 ``` **Common mistakes:** * Using an internal IP (`192.168.x.x`, `10.x.x.x`) - not routable from the internet * Using `0.0.0.0` - binds locally but is not a network address * Changing the IP without updating on-chain registration - Gateways lose contact A domain name is preferable to a bare IP. If the server's IP changes, a DNS record can be updated without a new on-chain registration transaction. ## Full Startup Command Replace every placeholder with actual values: ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} livepeer \ -network arbitrum-one-mainnet \ -ethUrl https://arb-mainnet.g.alchemy.com/v2/YOUR_API_KEY \ -ethAcctAddr YOUR_ETH_ADDRESS \ -orchestrator \ -transcoder \ -nvidia 0 \ -maxSessions 10 \ -pricePerUnit 1000 \ -serviceAddr YOUR_PUBLIC_IP:8935 ``` On first run with a new account (omitting `-ethAcctAddr`), go-livepeer prompts for a passphrase to create and encrypt a new keystore. This passphrase is required on every subsequent start. For verbose logging while getting started: ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} livepeer ... -v 6 ``` This outputs detailed logs including transcoding activity, RPC calls, and session events. ## Adding AI Inference To serve AI inference jobs alongside or instead of transcoding, three additional flags are needed. ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -aiWorker \ -aiModels /path/to/aiModels.json \ -aiModelsDir /path/to/models/ ``` Flag What it does `-aiWorker` Enables the AI worker component. Without this flag, go-livepeer ignores all AI configuration. `-aiModels` Path to `aiModels.json` - defines which pipelines and models to serve. Default: `~/.lpData/aiModels.json` `-aiModelsDir` Path to the directory where go-livepeer looks for cached model weights. Default: `~/.lpData/models/` `-aiRunnerImage` Optional. The Docker image for AI Runner containers. Defaults to `livepeer/ai-runner:latest`. Pin to a specific tag in production. **When running in Docker**, the AI Orchestrator needs access to the Docker socket to manage AI runner containers: ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} docker run \ --name livepeer_ai_orchestrator \ -v ~/.lpData/:/root/.lpData/ \ -v /var/run/docker.sock:/var/run/docker.sock \ --network host \ --gpus all \ livepeer/go-livepeer:master \ -orchestrator \ -serviceAddr 0.0.0.0:8936 \ -nvidia 0 \ -aiWorker \ -aiModels /root/.lpData/aiModels.json \ -aiModelsDir ~/.lpData/models ``` The AI Orchestrator uses port **8936** by default to avoid conflict with a transcoding Orchestrator on the same machine (which uses 8935). Set `-serviceAddr` accordingly. With Docker-out-of-Docker, the `-aiModelsDir` path must be a path on the **host machine**, not inside the container. Docker uses this path to mount model files into AI Runner containers it spawns. For the full guide to configuring `aiModels.json` and receiving the first AI job, see . ## Variants ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} docker run \ --name livepeer_orchestrator \ -v ~/.lpData/:/root/.lpData/ \ --network host \ --gpus all \ livepeer/go-livepeer:latest \ -network arbitrum-one-mainnet \ -ethUrl https://arb-mainnet.g.alchemy.com/v2/YOUR_API_KEY \ -orchestrator \ -transcoder \ -nvidia 0 \ -maxSessions 10 \ -pricePerUnit 1000 \ -serviceAddr YOUR_PUBLIC_IP:8935 ``` Mount `~/.lpData/` so the keystore and data persist between container restarts. Without this mount, a new ETH account is created on every run. Create `/etc/systemd/system/livepeer.service`: ```ini icon="code" title="/etc/systemd/system/livepeer.service" theme={"theme":{"light":"github-light","dark":"dark-plus"}} [Unit] Description=Livepeer Orchestrator After=network.target [Service] Type=simple User=ubuntu ExecStart=/usr/local/bin/livepeer \ -network arbitrum-one-mainnet \ -ethUrl https://arb-mainnet.g.alchemy.com/v2/YOUR_API_KEY \ -orchestrator \ -transcoder \ -nvidia 0 \ -maxSessions 10 \ -pricePerUnit 1000 \ -serviceAddr YOUR_PUBLIC_IP:8935 Restart=on-failure RestartSec=10 [Install] WantedBy=multi-user.target ``` Enable and start: ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} sudo systemctl daemon-reload sudo systemctl enable livepeer sudo systemctl start livepeer journalctl -u livepeer -f ``` go-livepeer does not have a native config file flag. The standard pattern stores flags in a plain text file and expands them at startup: ```bash icon="code" title="/etc/livepeer/livepeer.conf" theme={"theme":{"light":"github-light","dark":"dark-plus"}} -network arbitrum-one-mainnet -ethUrl https://arb-mainnet.g.alchemy.com/v2/YOUR_API_KEY -orchestrator -transcoder -nvidia 0 -maxSessions 10 -pricePerUnit 1000 -serviceAddr YOUR_PUBLIC_IP:8935 ``` ```bash icon="terminal" theme={"theme":{"light":"github-light","dark":"dark-plus"}} livepeer $(< /etc/livepeer/livepeer.conf) ``` In a systemd unit file, this requires an `ExecStart` wrapper shell script rather than calling the binary directly - systemd does not perform shell expansion in `ExecStart`. ## Next Steps Set up the Arbitrum RPC endpoint and fund the wallet with ETH for gas. Register the Orchestrator on-chain and enter the Active Set via `livepeer_cli`. Every flag, its type, default, and description.