Vercel AI Gateway

🌐 Global CDN / Anycast ● Vercel Global Anycast Edge Network

$5 free credit monthly · 100% list price passthrough with 0% markup

⚡ Speed & Latency
200ms ~ 350ms
Edge gateway by Vercel, the top choice for frontend & fullstack devs
🎁 Free Quota & Policy
$5 USD free team credit monthly (monthly refresh)
Instant GitHub OAuth access with zero credit card setup · Dozens of top models included
🛡️ Auth & Access Requirements
Unified OpenAI format · AI_GATEWAY_API_KEY
ai-gateway.vercel.sh/v1 native integration with Vercel AI SDK
📊 Concurrency & Context
High concurrency · 128K~1M context window
One unified gateway connecting dozens of upstream providers

🔌 OpenAI-Compatible Base URL

https://ai-gateway.vercel.sh/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
Vercel Free Tier gemini-2.5-flash
Google Gemini 2.5 Flash flagship multimodal model
Vercel Free Tier qwen-3.8-flash-next
Alibaba Qwen Flash-Next micro-architecture for speed
Deep Reasoning deepseek-v3.2-thinking
DeepSeek long-chain thinking with structured precision
Zhipu Flash glm-5.3-flash
Zhipu AI high-throughput flash architecture for coding & chat

💡 Key Traps & Practical Tips

$5 monthly compute credits (refreshes monthly)
GitHub 1-click login · No credit card · Premier model catalog
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://ai-gateway.vercel.sh/v1"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[
        [object Object]
    ]
)

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