Model calls in a sub-workspace

Scenarios

Control which models specific users can call: The API key for the default workspace can call all models, giving it excessive permissions. To control which models a RAM user can call, add the user to a sub-workspace, grant permissions for only the necessary models, and have them use that workspace's API key.
Allocate model call costs: Using the default workspace for multiple services or scenarios makes it difficult to distinguish the model call costs for each. Create a separate sub-workspace for each service or scenario to generate separate bills and simplify cost allocation.

Prerequisites

Get the API key for the sub-workspace: To call large model APIs, create an API key in the sub-workspace and set it as an environment variable named DASHSCOPE_API_KEY.
Set model call permissions (required for standard models): To call a standard model, such as qwen-plus, with the API key from a sub-workspace, you must first set model call permissions for that sub-workspace.
Note: Models that you fine-tune and deploy in Alibaba Cloud Model Studio do not require model call permissions. However, you can only call these models with the API key from their workspace.
Select a development language: Select a language and SDK that you are familiar with to call large model APIs.

Calling the model

OpenAI

Beijing
Singapore

SDK base_url: https://dashscope.aliyuncs.com/compatible-mode/v1HTTP endpoint: POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions

This example shows how to call the qwen-plus standard model in a sub-workspace using the OpenAI-compatible method. Unlike calls in the default workspace, you must use the API key from the sub-workspace.

Calling a model that has been fine-tuned on Alibaba Cloud Model Studio: You can call the model only by using DashScope. The OpenAI-compatible method is not supported.

Python (SDK)

import os
from openai import OpenAI

client = OpenAI(
    # If the environment variable is not set, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    # For a list of models, see https://help.aliyun.com/en/model-studio/models
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who are you?"},
    ]
)
print(completion.model_dump_json())

DashScope

China (Beijing)
Singapore region

HTTP endpoint:

Qwen large language models: POST https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation
Qwen-VL/Audio models: POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation

You do not need to configure base_url for SDK calls.

HTTP endpoint:

Qwen large language models: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation
Qwen-VL/OCR models: POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation

The base_url for SDK calls is:

Python
Java

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

Method 1:

import com.alibaba.dashscope.protocol.Protocol;
Generation gen = new Generation(Protocol.HTTP.getValue(), "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1");

Method 2:

import com.alibaba.dashscope.utils.Constants;
Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";

This example shows how to call the qwen-plus model in a sub-workspace using DashScope. The key difference from using the default workspace is that you must use the API key for the sub-workspace.

import os
import dashscope

messages = [
    {'role': 'system', 'content': 'You are a helpful assistant.'},
    {'role': 'user', 'content': 'Who are you?'}
]
response = dashscope.Generation.call(
    # If the environment variable is not set, replace the following line with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model="qwen-plus", # This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
    messages=messages,
    result_format='message'
    )
print(response)

// DashScope SDK v2.12.0 or later is recommended.
import java.util.Arrays;
import java.lang.System;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static GenerationResult callWithMessage() throws ApiException, NoApiKeyException, InputRequiredException {
        Generation gen = new Generation();
        Message systemMsg = Message.builder()
                .role(Role.SYSTEM.getValue())
                .content("You are a helpful assistant.")
                .build();
        Message userMsg = Message.builder()
                .role(Role.USER.getValue())
                .content("Who are you?")
                .build();
        GenerationParam param = GenerationParam.builder()
                // If the environment variable is not set, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
                .model("qwen-plus")
                .messages(Arrays.asList(systemMsg, userMsg))
                .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                .build();
        return gen.call(param);
    }
    public static void main(String[] args) {
        try {
            GenerationResult result = callWithMessage();
            System.out.println(JsonUtils.toJson(result));
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            // Use a logging framework to record the exception.
            System.err.println("An error occurred while calling the generation service: " + e.getMessage());
        }
        System.exit(0);
    }
}

<?php

$url = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation";
$apiKey = getenv('DASHSCOPE_API_KEY');

$data = [
    // This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
    "model" => "qwen-plus",
    "input" => [
        "messages" => [
            [
                "role" => "system",
                "content" => "You are a helpful assistant."
            ],
            [
                "role" => "user",
                "content" => "Who are you?"
            ]
        ]
    ],
    "parameters" => [
        "result_format" => "message"
    ]
];

$jsonData = json_encode($data);

$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $jsonData);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, [
    "Authorization: Bearer $apiKey",
    "Content-Type: application/json"
]);

$response = curl_exec($ch);
$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);

if ($httpCode == 200) {
    echo "Response: " . $response;
} else {
    echo "Error: " . $httpCode . " - " . $response;
}

curl_close($ch);
?>

DashScope does not provide a Node.js SDK. To make calls using the OpenAI Node.js SDK, see the OpenAI-compatible section.

import fetch from 'node-fetch';

const apiKey = process.env.DASHSCOPE_API_KEY;

const data = {
    model: "qwen-plus", // This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
    input: {
        messages: [
            {
                role: "system",
                content: "You are a helpful assistant."
            },
            {
                role: "user",
                content: "Who are you?"
            }
        ]
    },
    parameters: {
        result_format: "message"
    }
};

fetch('https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation', {
    method: 'POST',
    headers: {
        'Authorization': `Bearer ${apiKey}`,
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => {
    console.log(JSON.stringify(data));
})
.catch(error => {
    console.error('Error:', error);
});

using System.Net.Http.Headers;
using System.Text;

class Program
{
    private static readonly HttpClient httpClient = new HttpClient();

    static async Task Main(string[] args)
    {
        // If the environment variable is not set, replace the following line with your Model Studio API key: string? apiKey = "sk-xxx";
        string? apiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY");

        if (string.IsNullOrEmpty(apiKey))
        {
            Console.WriteLine("API key not set. Ensure the 'DASHSCOPE_API_KEY' environment variable is set.");
            return;
        }

        // Set the request URL and content.
        string url = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation";
        // This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
        string jsonContent = @"{
            ""model"": ""qwen-plus"",
            ""input"": {
                ""messages"": [
                    {
                        ""role"": ""system"",
                        ""content"": ""You are a helpful assistant.""
                    },
                    {
                        ""role"": ""user"",
                        ""content"": ""Who are you?""
                    }
                ]
            },
            ""parameters"": {
                ""result_format"": ""message""
            }
        }";

        // Send the request and get the response.
        string result = await SendPostRequestAsync(url, jsonContent, apiKey);

        // Print the result.
        Console.WriteLine(result);
    }

    private static async Task<string> SendPostRequestAsync(string url, string jsonContent, string apiKey)
    {
        using (var content = new StringContent(jsonContent, Encoding.UTF8, "application/json"))
        {
            // Set the request headers.
            httpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);
            httpClient.DefaultRequestHeaders.Accept.Add(new MediaTypeWithQualityHeaderValue("application/json"));

            // Send the request and get the response.
            HttpResponseMessage response = await httpClient.PostAsync(url, content);

            // Process the response.
            if (response.IsSuccessStatusCode)
            {
                return await response.Content.ReadAsStringAsync();
            }
            else
            {
                return $"Request failed: {response.StatusCode}";
            }
        }
    }
}

DashScope does not provide a Go SDK. To make calls using the OpenAI Go SDK, see the OpenAI-compatible section.

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
)

type Message struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

type Input struct {
	Messages []Message `json:"messages"`
}

type Parameters struct {
	ResultFormat string `json:"result_format"`
}

type RequestBody struct {
	Model      string     `json:"model"`
	Input      Input      `json:"input"`
	Parameters Parameters `json:"parameters"`
}

func main() {
	// Create an HTTP client.
	client := &http.Client{}

	// Build the request body.
	requestBody := RequestBody{
		// This example uses qwen-plus. You can replace it with another model name as needed. For a list of models, see: https://help.aliyun.com/en/model-studio/models
		Model: "qwen-plus",
		Input: Input{
			Messages: []Message{
				{
					Role:    "system",
					Content: "You are a helpful assistant.",
				},
				{
					Role:    "user",
					Content: "Who are you?",
				},
			},
		},
		Parameters: Parameters{
			ResultFormat: "message",
		},
	}

	jsonData, err := json.Marshal(requestBody)
	if err != nil {
		log.Fatal(err)
	}

	// Create a POST request.
	req, err := http.NewRequest("POST", "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation", bytes.NewBuffer(jsonData))
	if err != nil {
		log.Fatal(err)
	}

	// Set the request headers.
	// If the environment variable is not set, replace the following line with your Model Studio API key: apiKey := "sk-xxx"
	apiKey := os.Getenv("DASHSCOPE_API_KEY")
	req.Header.Set("Authorization", "Bearer "+apiKey)
	req.Header.Set("Content-Type", "application/json")

	// Send the request.
	resp, err := client.Do(req)
	if err != nil {
		log.Fatal(err)
	}
	defer resp.Body.Close()

	// Read the response body.
	bodyText, err := io.ReadAll(resp.Body)
	if err != nil {
		log.Fatal(err)
	}

	// Print the response content.
	fmt.Printf("%s\n", bodyText)
}

curl --location "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
    "model": "qwen-plus",
    "input":{
        "messages":[
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters": {
        "result_format": "message"
    }
}'

Error codes

If a model call returns an error, see Error Messages.

Next steps

Explore more models	The sample code uses the `qwen-plus` model. Model Studio also supports other Qwen modelsand third-party models like DeepSeek. Refer to Models for a list of supported models and their API reference.
Advanced usage	The sample code demonstrates a basic Q&A scenario. The Text generation overview covers advanced Qwen API features, including streaming output, structured output, and function calling.

​Scenarios

​Prerequisites

​Calling the model

​OpenAI

​DashScope

​Error codes