StepFun

🇨🇳 Direct Line ● 24h Uptime 99.8% (Enterprise Compute)

10M tokens free · Zero credit card requirements

🚀 Get Free Key ↗
⚡ Speed & Latency
180ms ~ 340ms
Direct AI supercomputer connection, strong multimodal intelligence
🎁 Free Quota & Policy
10,000,000 tokens granted upon registration
Quick mobile signup without card · Long-term validity
🛡️ Auth & Access Requirements
One-click API Key generation in console
Standard OpenAI-compatible protocol, ready out-of-the-box
📊 Concurrency & Context
Reliable concurrency · 8K~16K context
Proprietary Step series models excel in vision understanding & reasoning

🔌 OpenAI-Compatible Base URL

https://api.stepfun.com/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
高推理通用 step-1-8k
阶跃星辰通用旗舰大模型，逻辑与文学素养极佳
多模态视觉 step-1v-8k
图文双模态理解与图像剖析多模态旗舰
千亿旗舰 step-2-16k
万亿参数 MoE 架构深度思考旗舰

💡 Key Traps & Practical Tips

10 Million Free Tokens upon registration
Multimodal Step-1V flagship · Direct CN Line
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.stepfun.com/v1"
)

response = client.chat.completions.create(
    model="step-1-8k",
    messages=[
        [object Object]
    ]
)

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