Cloudflare Workers AI

🌐 Global Network ● 24h Uptime 99.9% (Global Anycast Edge)

10,000 neurons permanently free every day · Fraction of a cent afterwards

🚀 Get Free Key ↗
⚡ Speed & Latency
80ms ~ 260ms
Nearest connection via 300+ edge data centers worldwide, ultra-low latency
🎁 Free Quota & Policy
10,000 Neurons free compute refreshed daily
Permanent free tier · Resets at midnight UTC · Equivalent to thousands of queries
🛡️ Auth & Access Requirements
Cloudflare account generates API Token
OpenAI-compatible routing via /client/v4/accounts/{account_id}/ai/v1
📊 Concurrency & Context
Global distributed concurrency · No single bottleneck
Optimal for serverless edge workers, Telegram bots & automated scripts

🔌 OpenAI-Compatible Base URL

https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1

💡 Directly paste the address above as Base URL into any OpenAI-compatible client (NextChat, Cherry Studio, Immersive Translate, etc.).

📋 Featured Models:

Click Model ID to copy
边缘70B @cf/meta/llama-3.3-70b-instruct-fp8-fast
边缘优化加速版 Llama 3.3 70B 旗舰模型
推理蒸馏 @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
DeepSeek R1 蒸馏版 32B，兼具推理深度与响应速度
通义边缘 @cf/qwen/qwen2.5-7b-instruct
通义千问边缘高速轻量模型

💡 Key Traps & Practical Tips

10,000 Free Neurons refreshed daily
300+ Global edge nodes · Zero credit card
1. Protocol Compatibility: Most modern LLMs are fully OpenAI-compatible. In Python, simply use the official openai SDK for seamless switching.
2. Network Routing: Providers labeled Direct Connection respond in milliseconds domestically. Providers labeled Global Network are best called from servers with international access.
3. Local Key Security: When using tools on FreeAI Dog, all API Keys are strictly saved in your browser localStorage and never transmitted to any third-party server.

💻 Quick Python OpenAI SDK Example

from openai import OpenAI

client = OpenAI(
    api_key="your_api_key_here",  # 填入申请的 Key
    base_url="https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1"
)

response = client.chat.completions.create(
    model="@cf/meta/llama-3.3-70b-instruct-fp8-fast",
    messages=[
        [object Object]
    ]
)

print(response.choices[0].message.content)
← Radar ⚡ 🚀 🛠️ Everyday Life AI Toolbox (Plug & Play)