How is pricing calculated?

Standard is $0.004 per request; Premium models (Claude, GPT-4) are $0.008 per request; greenest adds a 10% surcharge; cache hits are free.

What is on-chain attestation?

Every inference produces a verifiable EAS attestation on Base including node location, energy price, carbon intensity, model used, and response hash.

How does x402 payment work?

If you call without an API key, the server returns HTTP 402 with USDC payment instructions on Base; your x402 client handles payment and proceeds with the request.

Windfall Inference

Verified

@papa-raw

npx machina-cli add skill @papa-raw/windfall-inference --openclaw

Files (1)

SKILL.md

2.6 KB

Windfall Inference

Spatially-routed LLM inference gateway for AI agents on Base. Routes every request to the cheapest model on the cleanest energy.

Setup

Set WINDFALL_API_KEY in your environment. Get one free at:

curl -X POST https://windfall.ecofrontiers.xyz/api/keys \
  -H "Content-Type: application/json" \
  -d '{"wallet_address": "YOUR_WALLET"}'

Keys with an ERC-8004 agent identity or Basename get 100 free requests. Anonymous keys get 25.

Usage

Use as an OpenAI-compatible endpoint. Set these two environment variables:

OPENAI_BASE_URL=https://windfall.ecofrontiers.xyz/v1
OPENAI_API_KEY=wf_YOUR_KEY

Or call directly:

curl https://windfall.ecofrontiers.xyz/v1/chat/completions \
  -H "Authorization: Bearer $WINDFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

x402 Payment (No API Key Needed)

Windfall supports the x402 payment protocol. Any agent with a Base wallet can pay per-request without creating an API key. Send a request without auth and the server returns HTTP 402 with a PAYMENT-REQUIRED header containing USDC payment instructions on Base. Your x402 client handles the rest.

Routing Modes

greenest (default) — lowest carbon intensity
cheapest — lowest energy cost
balanced — Pareto-weighted cost + carbon

Set via "mode" in the request body or X-Routing-Mode header.

Models

Default: DeepSeek V3 (auto-selected by engagement classifier). Override with "model" field. 200+ models available via OpenRouter.

Pricing

Standard: $0.004/request
Premium (Claude, GPT-4): $0.008/request
Green surcharge: +10% for greenest mode
Cache hits: free

Response Headers

Every response includes:

X-Windfall-Cache — HIT or MISS
X-Windfall-Mode — routing mode used
X-Windfall-Model — model that handled the request
X-Windfall-Node — node that executed the request
X-Windfall-Cost — cost charged
X-Windfall-Saved — savings vs direct API (cache hits)

Onchain Attestations

Every inference call produces a verifiable EAS attestation on Base with: node location, energy price, carbon intensity, model used, and response hash. Query at base.easscan.org.

Source

git clone https://clawhub.ai/papa-raw/windfall-inferenceView on GitHub

Overview

Windfall Inference is a spatially-routed LLM gateway for AI agents on Base. It routes every request to the cheapest model on the cleanest energy, supporting 200+ models via OpenRouter and exposing an OpenAI-compatible endpoint, with verifiable on-chain attestations on Base.

How This Skill Works

Clients call the OpenAI-compatible endpoint at OPENAI_BASE_URL. Windfall selects the model and routing mode (greenest, cheapest, or balanced) based on energy cost and carbon intensity, defaulting to DeepSeek V3. With 200+ models available and on-chain attestations on Base, each response includes headers like X-Windfall-Cost, X-Windfall-Mode, X-Windfall-Model, and X-Windfall-Node to show provenance and savings.

When to Use It

You aim to minimize carbon footprint and energy cost for sustainability targets.
You need predictable pricing at $0.004 per request, with optional premium models.
You want an OpenAI-compatible endpoint for Base-based agents without changing your client.
You want to pay per-request using x402 on Base, without creating an API key.
You require verifiable provenance via on-chain attestations for audits.

Quick Start

Step 1: Set WINDFALL_API_KEY in your environment (get a free key at the provided endpoint).
Step 2: Set OPENAI_BASE_URL=https://windfall.ecofrontiers.xyz/v1 and OPENAI_API_KEY=wf_YOUR_KEY.
Step 3: Call the /v1/chat/completions endpoint, optionally setting mode via the request body or X-Routing-Mode header (greenest, cheapest, or balanced).

Best Practices

Choose routing mode to match SLA: greenest for carbon, cheapest for cost, balanced for trade-offs.
Leverage cache hits to reduce cost and latency.
Monitor per-request costs and mode via X-Windfall-Cost and X-Windfall-Mode headers.
Securely store and rotate WINDFALL_API_KEY and OPENAI_API_KEY in your environment.
Use on-chain attestations (Base) to document model, energy, and provenance for compliance.

Example Use Cases

A climate-conscious app uses greenest mode to minimize carbon footprint while serving users.
A cost-sensitive enterprise routes to the cheapest model to lower operating expenses.
An agent on Base with an ERC-8004 identity demonstrates 100 free requests for compliant keys.
A developer deploys x402 payments, letting users pay in USDC on Base without API keys.
An audit-focused workflow validates model choice, energy price, and provenance via on-chain attestations.

Frequently Asked Questions

Add this skill to your agents