Replicate API
Replicate 接口
Run open-source ML models in the cloud. Supports Llama, Stable Diffusion, Whisper, and thousands more.
云端运行开源机器学习模型,支持 Llama、Stable Diffusion、Whisper 等数千个模型。
Website
Documentation
Pricing
pay-as-you-go (per prediction)
Authentication
- API Key
Popularity
73/100
Endpoints
https://api.replicate.com/v1/models
https://api.replicate.com/v1/predictions
SDKs
PythonNode.jscurl
Key Features
- ◆Thousands of open-source ML models
- ◆Llama, Stable Diffusion, Whisper
- ◆Serverless API with autoscaling
- ◆Custom model deployment
- ◆Pay-per-prediction pricing
Code Examples
Run Llama with Pythonpython
import replicate
output = replicate.run(
"meta/meta-llama-3.1-405b-instruct",
input={"prompt": "Hello!"}
)
for chunk in output:
print(chunk, end="")Tags
mlinferenceopen-source
Last updated: 2026-07-27
Get Started with Replicate API
Click below to visit the official website and start using this API.
Visit Replicate API →