Home / Big Tech / Requesty ⚡ Speed & Latency
220ms ~ 380ms
Global intelligent routing with smart failover dispatcher
🎁 Free Quota & Policy
200 free requests per day (20 RPM concurrency)
Resets daily · 12 curated models priced at $0 permanent free tier · No card required
🛡️ Auth & Access Requirements
Standard OpenAI SDK format · 1-click Bearer Key
router.requesty.ai (EU endpoint: router.eu.requesty.ai)
📊 Concurrency & Context
20 RPM concurrency · Up to 1M context window
Super and Ultra series all support 1M context
🔌 OpenAI-Compatible Base URL https://router.requesty.ai/v1 📋 Copy Base URL
💡 Directly paste the address above as Base URL into any OpenAI-compatible client (NextChat, Cherry Studio, Immersive Translate, etc.).
1M Free Context nvidia/nemotron-3-super-120b-a12b
NVIDIA 120B MoE agentic & complex reasoning flagship 📋 Copy Model ID
Omni Reasoning nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Multimodal chain-of-thought reasoning with rapid latency 📋 Copy Model ID
Google Open google/gemma-4-31b-it
Google 31B instruction-tuned open weights for code and math 📋 Copy Model ID
Coding Specialist poolside/laguna-xs.2
High-performance coding model optimized for agentic refactoring 📋 Copy Model ID
💡 Key Traps & Practical Tips 200 requests daily (resets daily)
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://router.requesty.ai/v1"
)
response = client.chat.completions.create(
model="nvidia/nemotron-3-super-120b-a12b",
messages=[
[object Object]
]
)
print(response.choices[0].message.content)