DeepInfra

🌐 Global Network ● 24h Uptime 99.8%

Generous initial testing credits · Very low minimum recharge

⚡ Speed & Latency
340ms ~ 680ms
Global distributed GPU serverless cluster, low first-token latency
🎁 Free Quota & Policy
Initial free testing credits granted upon signup
Email registration · No card required to start · Instant access
🛡️ Auth & Access Requirements
One-click API Key generation in dashboard
Standard /v1/openai compatible endpoint; zero code changes
📊 Concurrency & Context
Serverless elastic scaling · 128K context
One of the most affordable pay-as-you-go providers with high concurrency resilience

🔌 OpenAI-Compatible Base URL

https://api.deepinfra.com/v1/openai

💡 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
满血推理 deepseek-ai/DeepSeek-R1
DeepSeek-R1 满血深度逻辑思考旗舰
Meta旗舰 meta-llama/Meta-Llama-3.3-70B-Instruct
Meta 开源 70B 旗舰指令模型
通义增强 Qwen/Qwen2.5-72B-Instruct
通义千问 72B 高智力开源标杆

💡 Key Traps & Practical Tips

Free testing credits upon signup
Serverless pay-per-token with industry-lowest rates
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.deepinfra.com/v1/openai"
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1",
    messages=[
        [object Object]
    ]
)

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