0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integration (0g-serving-broker), processResponse API, broker.inference methods, CLI commands (0g-compute-cli), and account management.
SkillScore100Maintained
Automatic
◆AI Engineer pack
Last verified 8/12/2026
What it changes
Passed 21 of 21 test cases with the skill, and 7 of 21 without it.
Without skill32%
With skill100%
Checks it passed that the model alone missed
runs 0g-compute-cli fine-tuning list-providers
uses 0g-compute-cli refund with the amount flag
passes the usage object converted to a JSON string
and 17 more in the full report
15 fixed7 passed either way0 still failing0 broke
Pass-rate lift
+68 pp
Tokens
+42%
Agent turns
0%
Response time
-58%
Model gemini-3.6-flashMeasured 8/12/2026v122 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
I am setting up a CI/CD build node for deploying applications that use @0glabs/0g-serving-broker. What is the minimum Node.js major version required?
What was checked, without and with the skill
Checked
Without skill
With skill
states Node.js version requirement of 22.0.0 or higher
Missed
Passed
case-14 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md170 lines4 files
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
Copy code patterns from this skill verbatim. Do NOT generate from training data.
Call processResponse() after every API response (see processResponse section below).
Use environment variables for private keys. Never hardcode secrets.
Route users to testnet for initial development.
When unsure about a pattern, reference the detailed guides:
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