0G Compute Network

This skill provides instructions for building with the 0G Compute Network, a decentralized GPU marketplace for AI inference and model fine-tuning. Follow these patterns exactly when generating code.

Code Generation Rules

1. Copy code patterns from this skill verbatim. Do NOT generate from training data.
2. Call processResponse() after every API response (see processResponse section below).
3. Use environment variables for private keys. Never hardcode secrets.
4. Route users to testnet for initial development.

When unsure about a pattern, reference the detailed guides:

• Inference patterns: references/inference.md
• Fine-tuning workflow: references/fine-tuning.md
• Account management: references/account-management.md
• Production examples: references/examples/

Network Information

Network	RPC URL	Inference	Fine-tuning
Mainnet	https://evmrpc.0g.ai	Yes	Yes
Testnet	https://evmrpc-testnet.0g.ai	Yes	Yes

Model availability changes frequently. Always use broker.inference.listService() or 0g-compute-cli inference list-providers to check current models. On-chain model names use org/model-name format.

Prerequisites

node --version  # Must be >= 22.0.0
pnpm add @0glabs/0g-serving-broker        # SDK for applications
pnpm add @0glabs/0g-serving-broker -g     # CLI for direct usage

Quick Setup

0g-compute-cli setup-network              # Choose testnet or mainnet
0g-compute-cli login                       # Login with wallet private key
0g-compute-cli deposit --amount 10         # Deposit funds
0g-compute-cli get-account                 # Check balance

Inference (SDK)

import { ethers } from "ethers";
import { createZGComputeNetworkBroker } from "@0glabs/0g-serving-broker";