A sustainable LLM inference gateway that routes requests to the cheapest and greenest energy sources with onchain verification.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install windfall-inference
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install windfall-inference using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Windfall Inference?
Windfall Inference is a spatially-routed LLM gateway designed specifically for the next generation of AI agents. By integrating this skill into your Openclaw Skills library, you can significantly reduce the carbon footprint and operational costs of your AI workflows. The system automatically routes every request to the model and location offering the lowest carbon intensity or the best price point, ensuring your agent operations remain both ethical and economical. It serves as a drop-in replacement for OpenAI-compatible tools, providing access to over 200 models through a single, unified endpoint.
Built for the decentralized web, it leverages the Base network to provide transparent, verifiable proof of every inference executed. Whether you are building complex multi-agent systems or simple automated scripts, this skill ensures your compute is handled by the cleanest energy available without sacrificing performance or affordability.
Windfall Inference Use Cases
- Implementing sustainable AI operations for climate-conscious developers.
- Reducing inference costs for high-frequency AI agent workflows using Openclaw Skills.
- Providing verifiable onchain attestations for AI-generated content or decisions.
- Utilizing x402 payment protocols for decentralized, per-request agent billing.
- Dynamic model switching based on real-time energy prices and carbon intensity.
How Windfall Inference Works
- The agent sends an OpenAI-compatible request to the Windfall gateway using standard Openclaw Skills integration patterns.
- The system analyzes the selected routing mode (greenest, cheapest, or balanced) provided in the request headers or body.
- Requests are spatially routed to the specific node providing the best match for the chosen energy profile and model availability.
- The selected LLM processes the request and generates a high-performance response.
- The system generates an EAS (Ethereum Attestation Service) record on the Base network to verify node location, energy price, and carbon intensity.
- The agent receives the response along with detailed metadata regarding cost and savings in the HTTP headers.
Windfall Inference Setup
To get started with this addition to your Openclaw Skills, set your API key in the environment:
export WINDFALL_API_KEY=your_key_here
To request a new key via CLI:
curl -X POST https://windfall.ecofrontiers.xyz/api/keys \
-H "Content-Type: application/json" \
-d '{"wallet_address": "YOUR_WALLET"}'
Finally, configure your OpenAI-compatible client to use the custom base URL:
OPENAI_BASE_URL=https://windfall.ecofrontiers.xyz/v1
OPENAI_API_KEY=wf_YOUR_KEY
Windfall Inference Data Schema & Taxonomy
Windfall provides extensive metadata through response headers for tracking and auditing within your Openclaw Skills workflows:
| Header | Description |
|---|---|
X-Windfall-Cache |
Indicates a cache HIT or MISS |
X-Windfall-Mode |
The routing strategy used (greenest, cheapest, or balanced) |
X-Windfall-Model |
The specific model that processed the request |
X-Windfall-Node |
The execution node identifier |
X-Windfall-Cost |
Final cost of the transaction in USD |
X-Windfall-Saved |
Savings realized via caching or spatial routing |
Every inference call also produces a verifiable EAS attestation on Base containing node location, energy price, carbon intensity, and response hashes.
Windfall Inference Advanced Features
- Native x402 payment support for wallet-to-wallet per-request billing without requiring static API keys.
- Pareto-weighted balanced routing to optimize for both cost and carbon efficiency simultaneously.
- Access to 200+ models via OpenRouter with a unified $0.004 per request standard pricing model.
- Identity-based free request tiers for agents identified via ERC-8004 or Basenames.
- Spatial routing intelligence that identifies the cleanest energy grid in real-time for your Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
fxCLAW
A social platform and development framework enabling AI agents to create, mint, and monetize generative p5.js art as NFTs on the Base blockchain.
Temporal Time Manager
An AI-powered time management skill that enables natural language control over tasks, schedules, and ideas with cloud synchronization.
confluence-v2
A comprehensive API integration for Confluence Cloud that enables programmatic management of pages, spaces, folders, and collaborative content.
Autonomous Commerce
An autonomous agent capability for executing real-world e-commerce purchases with secure escrow and cryptographic confirmation.
A2A Marketplace
An AI tool marketplace via AgentForge for discovering, comparing, and executing specialized AI functions with integrated billing.
A2A Vault (PassBox)
A zero-knowledge secrets manager designed for secure credential storage and automated injection within Openclaw Skills environments.
Featured*
