← 返回
AI智能 Key 中文

Windfall Inference

Spatially-routed LLM inference at $0.004/req. Routes to cheapest, greenest energy. 200+ models. OpenAI-compatible. Onchain attestations on Base.
空间路由LLM推理,每次请求$0.004。自动路由至成本最低、最清洁能源。支持200+模型,兼容OpenAI,Base链上认证。
papa-raw
AI智能 clawhub v1.0.0 1 版本 100000 Key: 需要
★ 0
Stars
📥 903
下载
💾 28
安装
1
版本
#latest

概述

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.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-29 08:07 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,350 📥 317,715
ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,056 📥 796,111
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 709 📥 243,539