Alibaba Cloud Model Studio:Anthropic API compatibility

macOS

1. Run this command to check your shell type:

   echo $SHELL

2. Set environment variables for your shell:

   Zsh

   # Replace YOUR_DASHSCOPE_API_KEY with your Model Studio API Key.
   echo 'export ANTHROPIC_BASE_URL="https://dashscope-intl.aliyuncs.com/apps/anthropic"' >> ~/.zshrc
   echo 'export ANTHROPIC_API_KEY="YOUR_DASHSCOPE_API_KEY"' >> ~/.zshrc

   Bash

   # Replace YOUR_DASHSCOPE_API_KEY with your Model Studio API Key.
   echo 'export ANTHROPIC_BASE_URL="https://dashscope-intl.aliyuncs.com/apps/anthropic"' >> ~/.bash_profile
   echo 'export ANTHROPIC_API_KEY="YOUR_DASHSCOPE_API_KEY"' >> ~/.bash_profile

3. Apply the environment variables:

   Zsh

   source ~/.zshrc

   Bash

   source ~/.bash_profile

4. Verify environment variables in a new terminal:

   echo $ANTHROPIC_BASE_URL
   echo $ANTHROPIC_API_KEY

Windows

1. Set Model Studio's base URL and API key as environment variables:

   CMD

   1. Set environment variables in CMD:

      # Replace YOUR_DASHSCOPE_API_KEY with your DashScope API key
      setx ANTHROPIC_API_KEY "YOUR_DASHSCOPE_API_KEY"
      setx ANTHROPIC_BASE_URL "https://dashscope-intl.aliyuncs.com/apps/anthropic"

   2. Verify in a new CMD window:

      echo %ANTHROPIC_API_KEY%
      echo %ANTHROPIC_BASE_URL%

   PowerShell

   1. Set environment variables in PowerShell:

      # Replace YOUR_DASHSCOPE_API_KEY with your Model Studio API Key.
      [Environment]::SetEnvironmentVariable("ANTHROPIC_API_KEY", "YOUR_DASHSCOPE_API_KEY", [EnvironmentVariableTarget]::User)
      [Environment]::SetEnvironmentVariable("ANTHROPIC_BASE_URL", "https://dashscope-intl.aliyuncs.com/apps/anthropic", [EnvironmentVariableTarget]::User)

   2. Verify in a new PowerShell window:

      echo $env:ANTHROPIC_API_KEY
      echo $env:ANTHROPIC_BASE_URL

cURL

curl -X POST "https://dashscope-intl.aliyuncs.com/apps/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "x-api-key: ${ANTHROPIC_API_KEY}" \
  -d '{
    "model": "qwen-plus",
    "max_tokens": 1024,
    "stream": true,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 1024
    },
    "system": "You are a helpful assistant",
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Who are you?"
                }
            ]
        }
    ]
}'

Python

1. Install Anthropic SDK

   pip install anthropic

2. Example

   import anthropic
   import os
   
   client = anthropic.Anthropic(
       api_key=os.getenv("ANTHROPIC_API_KEY"),
       base_url=os.getenv("ANTHROPIC_BASE_URL"),
   )
   
   message = client.messages.create(
       model="qwen-plus",
       max_tokens=1024,
       stream=True,
       system="you are a helpful assistant",
       # Deep thinking is supported by some models only. See the supported models list.
       thinking={
           "type": "enabled",
           "budget_tokens": 1024
       },
       messages=[
           {
               "role": "user",
               "content": [
                   {
                       "type": "text",
                       "text": "Who are you?"
                   }
               ]
           }
       ]
   )
   
   print("=== Thinking Process ===")
   first_text = True
   for chunk in message:
       if chunk.type == "content_block_delta":
           if hasattr(chunk.delta, 'thinking'):
               print(chunk.delta.thinking, end="", flush=True)
           elif hasattr(chunk.delta, 'text'):
               if first_text:
                   print("\n\n=== Answer ===")
                   first_text = False
               print(chunk.delta.text, end="", flush=True)
   

TypeScript

1. Install Anthropic TypeScript SDK

   npm install @anthropic-ai/sdk

2. Example

   import Anthropic from "@anthropic-ai/sdk";
   
   async function main() {
     const anthropic = new Anthropic({
       apiKey: process.env.ANTHROPIC_API_KEY,
       baseURL: process.env.ANTHROPIC_BASE_URL,
     });
   
     const stream = await anthropic.messages.create({
       model: "qwen-plus",
       max_tokens: 1024,
       stream: true,
       // Deep thinking is supported by some models only. See the list of supported models.
       thinking: { type: "enabled", budget_tokens: 1024 },
       system: "You are a helpful assistant",
       messages: [{ 
         role: "user", 
         content: [
           {
             type: "text",
             text: "Who are you?"
           }
         ]
       }]
     });
   
     console.log("=== Thinking Process ===");
     let firstText = true;
   
     for await (const chunk of stream) {
       if (chunk.type === "content_block_delta") {
         if ('thinking' in chunk.delta) {
           process.stdout.write(chunk.delta.thinking);
         } else if ('text' in chunk.delta) {
           if (firstText) {
             console.log("\n\n=== Answer ===");
             firstText = false;
           }
           process.stdout.write(chunk.delta.text);
         }
       }
     }
     console.log();
   }
   
   main().catch(console.error);