Hugging Face Serverless InferenceHugging Face (Serverless API)
Official Serverless Inference API by Hugging Face. Free access to 300+ open-source models with 300 req/hr tier.
Core Free Tier
300 次 / 小时 Requests (永久免费)每日刷新
免费层提供每小时 300 次请求，覆盖 Hugging Face 托管的数百款前沿开源大模型，完全兼容 OpenAI 格式。
Reset Cycle: 每小时重置
Eligibility & Verification Requirements
Phone VerificationNo Phone Needed
Credit CardNo Card Needed
Network / RegionGlobal Direct
Concurrency RateStandard Tier
10-Second Drop-in Integration Code (OpenAI Compatible)
curl https://api-inference.huggingface.co/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "deepseek-ai/DeepSeek-R1",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api-inference.huggingface.co/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-R1",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api-inference.huggingface.co/v1",
apiKey: "YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "deepseek-ai/DeepSeek-R1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Gotchas & Risk Precautions
- 冷门模型可能存在冷启动排队延迟。
- 高并发请添加重试机制。
