Skip to main content

​
1. Log in to the platform

Visit SiliconCloud Official Websiteand click the “Login” button in the top right corner. Follow the prompts to fill in your basic information for login. (Note: Currently, the platform supports login via SMS, email, as well as OAuth login through GitHub and Google.)

​
2. View model lists and details

Visit theModels to view the details of currently available models, including model prices and the highest speed limit available to users. You can also access the model experience center from the model details page by clicking “Online Experience”.

​
3. Experience GenAI capabilities in the playground

Enter theExperience Center (playground)page.On the left sidebar, you can select language models, text-to-image models, and image-to-image models. Select the appropriate model to start real-time experience. Input relevant parameters and prompt, then click the “Run” button to see the model’s generated results.

​
4. Use SiliconCloud API to call GenAI capabilities

​
4.1 Create API Key

Go to the API Keys, click on “Create API Key,” and create your API key.

​
4.2 Call services via REST interface

You can directly use your API key in the API Documentation on the platform for online calls, where you can generate corresponding code snippets.

​
4.3 Call via OpenAI interface

Currently, part of the large language models support calling via the openai library. After installing Python 3.7.1 or higher and setting up a virtual environment, you can install the OpenAI Python library. Run the following command from the terminal/command line: 
pip install --upgrade openai
After completing this operation, running the command will display the Python libraries installed in your current environment, confirming that the OpenAI Python library has been successfully installed. You can then directly call the relevant interfaces via OpenAI. Currently, the platform supports most parameters related to OpenAI. 
from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY_FROM_CLOUD_SILICONFLOW_CN", 
                base_url="https://api.siliconflow.cn/v1")
response = client.chat.completions.create(
    # model='Pro/deepseek-ai/DeepSeek-R1',
    model="Qwen/Qwen2.5-72B-Instruct",
    messages=[
        {'role': 'user', 
        'content': "What New Opportunities Will Inference Models Bring to the Market?"}
    ],
    stream=True
)

for chunk in response:
    if not chunk.choices:
        continue
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.choices[0].delta.reasoning_content:
        print(chunk.choices[0].delta.reasoning_content, end="", flush=True)
⌘I