Model Invocation¶

The d.run platform offers two deployment options for large language models, allowing you to choose based on your specific needs:

• MaaS by Token: Utilizes token-based billing, sharing resources, and enables model invocation without requiring instance deployment
• Model Service: Provides dedicated instances with per-instance billing, offering unlimited API call access

Supported Models and Deployment Options¶

Model Endpoints¶

A model endpoint is a URL or API address that allows users to access and send requests for model inference.

API Invocation Examples¶

Invoking via MaaS by Token¶

To invoke models using the MaaS by Token method, follow these steps:

1. Obtain API Key: Log in to your user console and create a new API Key
2. Set Endpoint: Replace the SDK endpoint with chat.d.run
3. Invoke Model: Use the official model name along with the new API Key for invocation

Example Code (Python):

import openai

openai.api_key = "your-api-key"  # Replace with your API Key
openai.api_base = "https://chat.d.run"

response = openai.Completion.create(
  model="public/deepseek-r1",
  prompt="What is your name?"
)

print(response.choices[0].text)

Invoking via Model Service¶

To invoke models using the Model Service method, follow these steps:

1. Obtain API Key: Log in to your user console and create a new API Key
2. Set Endpoint: Replace the SDK endpoint with <region>.d.run
3. Invoke Model: Use the official model name along with the new API Key for invocation

Example Code (Python):

import openai

openai.api_key = "your-api-key"  # Replace with your API Key
openai.api_base = "<region>.d.run"

response = openai.Completion.create(
  model="u-1100a15812cc/qwen2",
  prompt="What is your name?"
)

print(response.choices[0].text)

Support and Feedback¶

For any questions or feedback, please contact our Technical Support Team.