Request body
|
Text input
Pythonimport os
from dashscope import MultiModalConversation
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{'role': 'system', 'content': [{'text': 'You are a helpful assistant.'}]},
{'role': 'user', 'content': [{'text': 'Who are you?'}]}
]
response = MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen3.8-max", # This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages,
)
print(response)
Java// We recommend that you use DashScope SDK V2.12.0 or later.
import java.util.Arrays;
import java.util.Collections;
import java.lang.System;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public static MultiModalConversationResult callWithMessage() throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage systemMsg = MultiModalMessage.builder()
.role(Role.SYSTEM.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant.")))
.build();
MultiModalMessage userMsg = MultiModalMessage.builder()
.role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "Who are you?")))
.build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen3.8-max")
.messages(Arrays.asList(systemMsg, userMsg))
.build();
return conv.call(param);
}
public static void main(String[] args) {
try {
MultiModalConversationResult result = callWithMessage();
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | UploadFileException e) {
// Use a logging framework to record the exception information.
System.err.println("An error occurred while calling the generation service: " + e.getMessage());
}
System.exit(0);
}
}
PHP (HTTP)<?php
$url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation";
$apiKey = getenv('DASHSCOPE_API_KEY');
$data = [
// This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
"model" => "qwen3.8-max",
"input" => [
"messages" => [
[
"role" => "system",
"content" => [["text" => "You are a helpful assistant."]]
],
[
"role" => "user",
"content" => [["text" => "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);
?>
Node.js (HTTP)
DashScope does not provide an SDK for the Node.js environment. To make calls using the OpenAI Node.js SDK, see the OpenAI section in this topic. import fetch from 'node-fetch';
const apiKey = process.env.DASHSCOPE_API_KEY;
const data = {
model: "qwen3.8-max", // This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
input: {
messages: [
{
role: "system",
content: [{"text": "You are a helpful assistant."}]
},
{
role: "user",
content: [{"text": "Who are you?"}]
}
]
},
parameters: {
result_format: "message"
}
};
fetch('https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-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);
});
C# (HTTP)using System.Net.Http.Headers;
using System.Text;
class Program
{
private static readonly HttpClient httpClient = new HttpClient();
static async Task Main(string[] args)
{
// If you have not configured an environment variable, 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("The API key is not set. Make sure that the 'DASHSCOPE_API_KEY' environment variable is set.");
return;
}
// Set the request URL and content.
string url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation";
// This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
string jsonContent = @"{
""model"": ""qwen3.8-max"",
""input"": {
""messages"": [
{
""role"": ""system"",
""content"": [{""text"": ""You are a helpful assistant.""}]
},
{
""role"": ""user"",
""content"": [{""text"": ""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}";
}
}
}
}
Go (HTTP)
DashScope does not provide an SDK for Go. To make calls using the OpenAI Go SDK, see the OpenAI-Go section in this topic. package main
import (
"bytes"
"encoding/json"
"fmt"
"io"
"log"
"net/http"
"os"
)
type ContentItem struct {
Text string `json:"text"`
}
type Message struct {
Role string `json:"role"`
Content []ContentItem `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 qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
Model: "qwen3.8-max",
Input: Input{
Messages: []Message{
{
Role: "system",
Content: []ContentItem{{Text: "You are a helpful assistant."}},
},
{
Role: "user",
Content: []ContentItem{{Text: "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://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation", bytes.NewBuffer(jsonData))
if err != nil {
log.Fatal(err)
}
// Set the request headers.
// If you have not configured an environment variable, 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)
}
curlcurl --location "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "qwen3.8-max",
"input":{
"messages":[
{
"role": "system",
"content": [{"text": "You are a helpful assistant."}]
},
{
"role": "user",
"content": [{"text": "Who are you?"}]
}
]
},
"parameters": {
"result_format": "message"
}
}'
Streaming output
For more information, see Streaming output.
Text generation models
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{'role':'system','content':'you are a helpful assistant'},
{'role': 'user','content': 'Who are you?'}
]
responses = dashscope.Generation.call(
# If you have not configured an environment variable, 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; replace with any other text-generation model as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages,
result_format='message',
stream=True,
incremental_output=True
)
for response in responses:
print(response)
Javaimport java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
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;
import io.reactivex.Flowable;
import java.lang.System;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
private static final Logger logger = LoggerFactory.getLogger(Main.class);
private static void handleGenerationResult(GenerationResult message) {
System.out.println(JsonUtils.toJson(message));
}
public static void streamCallWithMessage(Generation gen, Message userMsg)
throws NoApiKeyException, ApiException, InputRequiredException {
GenerationParam param = buildGenerationParam(userMsg);
Flowable<GenerationResult> result = gen.streamCall(param);
result.blockingForEach(message -> handleGenerationResult(message));
}
private static GenerationParam buildGenerationParam(Message userMsg) {
return GenerationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen-plus; replace with any other text-generation model as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen-plus")
.messages(Arrays.asList(userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.incrementalOutput(true)
.build();
}
public static void main(String[] args) {
try {
Generation gen = new Generation();
Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you?").build();
streamCallWithMessage(gen, userMsg);
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
logger.error("An exception occurred: {}", e.getMessage());
}
System.exit(0);
}
}
curlcurl --location "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--header "X-DashScope-SSE: enable" \
--data '{
"model": "qwen-plus",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Who are you?"
}
]
},
"parameters": {
"result_format": "message",
"incremental_output":true
}
}'
Multimodal models
Python
import os
from dashscope import MultiModalConversation
import dashscope
# If you use a model in the Singapore region, uncomment the following line.
# dashscope.base_http_api_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1"
messages = [
{
"role": "user",
"content": [
{"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
{"text": "What is depicted in the image?"}
]
}
]
responses = MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://help.aliyun.com/en/model-studio/get-api-key
api_key=os.getenv("DASHSCOPE_API_KEY"),
model='qwen3-vl-plus', # You can replace this with another multimodal model and modify the messages accordingly.
messages=messages,
stream=True,
incremental_output=True
)
full_content = ""
print("Streaming output content:")
for response in responses:
if response.output.choices[0].message.content:
print(response.output.choices[0].message.content[0]['text'])
full_content += response.output.choices[0].message.content[0]['text']
print(f"Full content: {full_content}")
Java
import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import io.reactivex.Flowable;
import com.alibaba.dashscope.utils.Constants;
public class Main {
// If you use a model in the Singapore region, uncomment the following line.
// static {Constants.baseHttpApiUrl="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";}
public static void streamCall()
throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("image", "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"),
Collections.singletonMap("text", "What is depicted in the image?"))).build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
// The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://help.aliyun.com/en/model-studio/get-api-key
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen3-vl-plus") // You can replace this with another multimodal model and modify the messages accordingly.
.messages(Arrays.asList(userMessage))
.incrementalOutput(true)
.build();
Flowable<MultiModalConversationResult> result = conv.streamCall(param);
result.blockingForEach(item -> {
try {
var content = item.getOutput().getChoices().get(0).getMessage().getContent();
// Check if content exists and is not empty.
if (content != null && !content.isEmpty()) {
System.out.println(content.get(0).get("text"));
}
} catch (Exception e) {
System.out.println(e.getMessage());
}
});
}
public static void main(String[] args) {
try {
streamCall();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
curl
# ======= Important =======
# The API keys for the Singapore and China (Beijing) regions are different. To obtain an API key, see https://help.aliyun.com/en/model-studio/get-api-key
# The following is the URL for the China (Beijing) region. If you use a model in the Singapore region, replace the URL with: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# === Delete this comment before execution ===
curl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
"model": "qwen3-vl-plus",
"input":{
"messages":[
{
"role": "user",
"content": [
{"image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"},
{"text": "What is depicted in the image?"}
]
}
]
},
"parameters": {
"incremental_output": true
}
}'
Image input
For more information about how to use large models to analyze images, see Image and video understanding.
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{
"role": "user",
"content": [
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
{"text": "What are these?"}
]
}
]
response = dashscope.MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen-vl-max', # This example uses qwen-vl-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages
)
print(response)
Java// Copyright (c) Alibaba, Inc. and its affiliates.
import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public static void simpleMultiModalConversationCall()
throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
.content(Arrays.asList(
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"),
Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"),
Collections.singletonMap("text", "What are these?"))).build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen-vl-plus. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen-vl-plus")
.message(userMessage)
.build();
MultiModalConversationResult result = conv.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
simpleMultiModalConversationCall();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
curlcurl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-vl-plus",
"input":{
"messages":[
{
"role": "user",
"content": [
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/tiger.png"},
{"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/rabbit.png"},
{"text": "What are these?"}
]
}
]
}
}'
Video input
The following code shows an example of how to pass video frames. For more information about other methods, such as passing a video file, see Visual understanding.
Pythonfrom http import HTTPStatus
import os
# DashScope V1.20.10 or later is required.
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [{"role": "user",
"content": [
{"video":["https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"]},
{"text": "Describe the process in this video"}]}]
response = dashscope.MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv("DASHSCOPE_API_KEY"),
model='qwen-vl-max', # This example uses qwen-vl-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages
)
if response.status_code == HTTPStatus.OK:
print(response)
else:
print(response.code)
print(response.message)
Java// DashScope SDK V2.16.7 or later is required.
import java.util.Arrays;
import java.util.Collections;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
// This example uses qwen-vl-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
private static final String MODEL_NAME = "qwen-vl-max";
public static void videoImageListSample() throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage systemMessage = MultiModalMessage.builder()
.role(Role.SYSTEM.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant.")))
.build();
MultiModalMessage userMessage = MultiModalMessage.builder()
.role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("video", Arrays.asList("https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg")),
Collections.singletonMap("text", "Describe the process in this video")))
.build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
.model(MODEL_NAME).message(systemMessage)
.message(userMessage).build();
MultiModalConversationResult result = conv.call(param);
System.out.print(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
videoImageListSample();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
curlcurl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "qwen-vl-max",
"input": {
"messages": [
{
"role": "user",
"content": [
{
"video": [
"https://img.alicdn.com/imgextra/i3/O1CN01K3SgGo1eqmlUgeE9b_!!6000000003923-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01BjZvwg1Y23CF5qIRB_!!6000000003000-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i4/O1CN01Ib0clU27vTgBdbVLQ_!!6000000007859-0-tps-3840-2160.jpg",
"https://img.alicdn.com/imgextra/i1/O1CN01aygPLW1s3EXCdSN4X_!!6000000005710-0-tps-3840-2160.jpg"
]
},
{
"text": "Describe the process in this video"
}
]
}
]
}
}'
Audio input
Audio understanding
For more information about how to use large models to analyze audio, see Audio understanding - Qwen-Audio.
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{
"role": "user",
"content": [
{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
{"text": "What is this audio about?"}
]
}
]
response = dashscope.MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen-audio-turbo', # This example uses qwen-audio-turbo. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages
)
print(response)
Javaimport java.util.Arrays;
import java.util.Collections;
import java.lang.System;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public static void simpleMultiModalConversationCall()
throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"),
Collections.singletonMap("text", "What is this audio about?"))).build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen-audio-turbo. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen-audio-turbo")
.message(userMessage)
.build();
MultiModalConversationResult result = conv.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
simpleMultiModalConversationCall();
} catch (ApiException | NoApiKeyException | UploadFileException e) {
System.out.println(e.getMessage());
}
System.exit(0);
}
}
curlcurl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-audio-turbo",
"input":{
"messages":[
{
"role": "system",
"content": [
{"text": "You are a helpful assistant."}
]
},
{
"role": "user",
"content": [
{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
{"text": "What is this audio about?"}
]
}
]
}
}'
Web search
Pythonimport os
from dashscope import MultiModalConversation
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{'role': 'system', 'content': [{'text': 'You are a helpful assistant.'}]},
{'role': 'user', 'content': [{'text': 'What is the weather in Hangzhou tomorrow?'}]}
]
response = MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen3.8-max", # This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages,
enable_search=True,
)
print(response)
Java// We recommend that you use DashScope SDK V2.12.0 or later.
import java.util.Arrays;
import java.util.Collections;
import java.lang.System;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.JsonUtils;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public static MultiModalConversationResult callWithMessage() throws ApiException, NoApiKeyException, UploadFileException {
MultiModalConversation conv = new MultiModalConversation();
MultiModalMessage systemMsg = MultiModalMessage.builder()
.role(Role.SYSTEM.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant.")))
.build();
MultiModalMessage userMsg = MultiModalMessage.builder()
.role(Role.USER.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "What is the weather in Hangzhou tomorrow?")))
.build();
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen3.8-max")
.messages(Arrays.asList(systemMsg, userMsg))
.enableSearch(true)
.build();
return conv.call(param);
}
public static void main(String[] args) {
try {
MultiModalConversationResult result = callWithMessage();
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | UploadFileException e) {
// Use a logging framework to record the exception information.
System.err.println("An error occurred while calling the generation service: " + e.getMessage());
}
System.exit(0);
}
}
curlcurl -X POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-max",
"input":{
"messages":[
{
"role": "system",
"content": [{"text": "You are a helpful assistant."}]
},
{
"role": "user",
"content": [{"text": "What is the weather in Hangzhou tomorrow?"}]
}
]
},
"parameters": {
"enable_search": true,
"result_format": "message"
}
}'
Tool calling
For the complete code of the function calling process, see Function Calling.
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
tools = [
{
"type": "function",
"function": {
"name": "get_current_time",
"description": "Useful when you want to know the current time.",
"parameters": {}
}
},
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Useful when you want to query the weather in a specific city.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "A city or district, such as Beijing, Hangzhou, or Yuhang District."
}
}
},
"required": [
"location"
]
}
}
]
messages = [{"role": "user", "content": [{"text": "What is the weather like in Hangzhou"}]}]
response = dashscope.MultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen3.8-max', # This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=messages,
tools=tools,
)
print(response)
Javaimport java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import com.alibaba.dashscope.aigc.conversation.ConversationParam.ResultFormat;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import java.util.Collections;
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.tools.FunctionDefinition;
import com.alibaba.dashscope.tools.ToolFunction;
import com.alibaba.dashscope.utils.JsonUtils;
import com.fasterxml.jackson.databind.node.ObjectNode;
import com.github.victools.jsonschema.generator.Option;
import com.github.victools.jsonschema.generator.OptionPreset;
import com.github.victools.jsonschema.generator.SchemaGenerator;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfig;
import com.github.victools.jsonschema.generator.SchemaGeneratorConfigBuilder;
import com.github.victools.jsonschema.generator.SchemaVersion;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public class GetWeatherTool {
private String location;
public GetWeatherTool(String location) {
this.location = location;
}
public String call() {
return location+" is sunny today";
}
}
public class GetTimeTool {
public GetTimeTool() {
}
public String call() {
LocalDateTime now = LocalDateTime.now();
DateTimeFormatter formatter = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
String currentTime = "Current time: " + now.format(formatter) + ".";
return currentTime;
}
}
public static void SelectTool()
throws NoApiKeyException, ApiException, InputRequiredException {
SchemaGeneratorConfigBuilder configBuilder =
new SchemaGeneratorConfigBuilder(SchemaVersion.DRAFT_2020_12, OptionPreset.PLAIN_JSON);
SchemaGeneratorConfig config = configBuilder.with(Option.EXTRA_OPEN_API_FORMAT_VALUES)
.without(Option.FLATTENED_ENUMS_FROM_TOSTRING).build();
SchemaGenerator generator = new SchemaGenerator(config);
ObjectNode jsonSchema_weather = generator.generateSchema(GetWeatherTool.class);
ObjectNode jsonSchema_time = generator.generateSchema(GetTimeTool.class);
FunctionDefinition fdWeather = FunctionDefinition.builder().name("get_current_weather").description("Get the weather for a specified region")
.parameters(JsonUtils.parseString(jsonSchema_weather.toString()).getAsJsonObject()).build();
FunctionDefinition fdTime = FunctionDefinition.builder().name("get_current_time").description("Get the current time")
.parameters(JsonUtils.parseString(jsonSchema_time.toString()).getAsJsonObject()).build();
MultiModalMessage systemMsg = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
.content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant. When asked a question, use tools wherever possible.")))
.build();
MultiModalMessage userMsg = MultiModalMessage.builder().role(Role.USER.getValue()).content(Arrays.asList(Collections.singletonMap("text", "Weather in Hangzhou"))).build();
List<MultiModalMessage> messages = new ArrayList<>();
messages.addAll(Arrays.asList(systemMsg, userMsg));
MultiModalConversationParam param = MultiModalConversationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
// This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
.model("qwen3.8-max")
.messages(messages)
.tools(Arrays.asList(
ToolFunction.builder().function(fdWeather).build(),
ToolFunction.builder().function(fdTime).build()))
.build();
MultiModalConversation conv = new MultiModalConversation();
MultiModalConversationResult result = conv.call(param);
System.out.println(JsonUtils.toJson(result));
}
public static void main(String[] args) {
try {
SelectTool();
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.out.println(String.format("Exception %s", e.getMessage()));
}
System.exit(0);
}
}
curlcurl --location "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "qwen3.8-max",
"input": {
"messages": [{
"role": "user",
"content": [{"text": "What is the weather like in Hangzhou"}]
}]
},
"parameters": {
"result_format": "message",
"tools": [{
"type": "function",
"function": {
"name": "get_current_time",
"description": "Useful when you want to know the current time.",
"parameters": {}
}
},{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Useful when you want to query the weather in a specific city.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "A city or district, such as Beijing, Hangzhou, or Yuhang District."
}
}
},
"required": ["location"]
}
}]
}
}'
Asynchronous invocation# Your Dashscope Python SDK version must be 1.19.0 or later.
import asyncio
import platform
import os
from dashscope.aigc.multimodal_conversation import AioMultiModalConversation
async def main():
response = await AioMultiModalConversation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen3.8-max", # This example uses qwen3.8-max. You can replace it with another model name as needed. For a list of models, see https://help.aliyun.com/en/model-studio/getting-started/models
messages=[{"role": "user", "content": [{"text": "Who are you"}]}],
)
print(response)
if platform.system() == "Windows":
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
asyncio.run(main())
Document understanding
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
messages = [
{'role': 'system', 'content': 'you are a helpful assisstant'},
# Replace {FILE_ID} with the file ID used in your actual conversation scenario.
{'role':'system','content':f'fileid://{FILE_ID}'},
{'role': 'user', 'content': 'What is this article about'}]
response = dashscope.Generation.call(
# If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
api_key=os.getenv('DASHSCOPE_API_KEY'),
model="qwen-long",
messages=messages,
result_format='message'
)
print(response)
Javaimport java.util.Arrays;
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;
import com.alibaba.dashscope.utils.Constants;
public class Main {
static {Constants.baseHttpApiUrl="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";}
public static GenerationResult callWithFile() throws ApiException, NoApiKeyException, InputRequiredException {
Generation gen = new Generation();
Message systemMsg = Message.builder()
.role(Role.SYSTEM.getValue())
.content("you are a helpful assistant")
.build();
Message fileSystemMsg = Message.builder()
.role(Role.SYSTEM.getValue())
// Replace {FILE_ID} with the file ID used in your actual conversation scenario.
.content("fileid://{FILE_ID}")
.build();
Message userMsg = Message.builder()
.role(Role.USER.getValue())
.content("What is this article about")
.build();
GenerationParam param = GenerationParam.builder()
// If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
.apiKey(System.getenv("DASHSCOPE_API_KEY"))
.model("qwen-long")
.messages(Arrays.asList(systemMsg, fileSystemMsg, userMsg))
.resultFormat(GenerationParam.ResultFormat.MESSAGE)
.build();
return gen.call(param);
}
public static void main(String[] args) {
try {
GenerationResult result = callWithFile();
System.out.println(JsonUtils.toJson(result));
} catch (ApiException | NoApiKeyException | InputRequiredException e) {
System.err.println("Error calling DashScope API: " + e.getMessage());
e.printStackTrace();
}
}
}
curl
Replace {FILE_ID} with the file ID that is used in your actual conversation scenario. curl --location "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "qwen-long",
"input":{
"messages":[
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "system",
"content": "fileid://{FILE_ID}"
},
{
"role": "user",
"content": "What is this article about?"
}
]
},
"parameters": {
"result_format": "message"
}
}'
PPT generation
Only the qwen-doc-turbo model supports PPT generation. For more information, see Generate a PPT.
Pythonimport os
import dashscope
dashscope.base_http_api_url = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1"
response = dashscope.Generation.call(
api_key=os.getenv('DASHSCOPE_API_KEY'),
model='qwen-doc-turbo',
messages=[
{"role": "system", "content": "you are a helpful assistant."},
{"role": "system", "content": "Your document content"},
{"role": "user", "content": "Generate a 10- to 20-page PPT"}
],
skill=[{"type": "ppt", "mode": "general", "template_id": "news_01"}]
)
try:
if response.status_code == 200:
print(response.output.choices[0].message.content)
else:
print(f"Request failed, status code: {response.status_code}")
print(f"Error message: {response.message}")
print("For more information, see https://help.aliyun.com/en/model-studio/developer-reference/error-code")
except Exception as e:
print(f"An error occurred: {e}")
print("For more information, see https://help.aliyun.com/en/model-studio/developer-reference/error-code")
curlcurl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $DASHSCOPE_API_KEY' \
--header 'X-DashScope-SSE: enable' \
--data '{
"model": "qwen-doc-turbo",
"input": {
"messages": [
{
"role": "system",
"content": "you are a helpful assistant."
},
{
"role": "system",
"content": "Your document content"
},
{
"role": "user",
"content": "Generate a 10- to 20-page PPT"
}
]
},
"parameters": {
"skill": [
{
"type": "ppt",
"mode": "general",
"template_id": "news_01"
}
]
}
}'
|
|
model string (Required)
The name of the model to use.
Supported models include Qwen large language models (commercial and open source editions), Qwen-VL, Qwen-Coder, Qwen-Audio, math models, DeepSeek (provided by Alibaba Cloud and SiliconFlow), Kimi (provided by Alibaba Cloud), GLM (provided by Alibaba Cloud), and MiniMax (provided by Alibaba Cloud and MiniMax).
For specific model names and billing details, see Select a model.
|
|
messages array (Required)
The context to pass to the large language model (LLM), arranged in conversational order.
When you call over HTTP, place messages in the input object.
Message types
System Message object (Optional)
A system message that is used to set the role, tone, task objectives, or constraints for the LLM. It is usually placed first in the messages array.
We do not recommend that you set a system message for QwQ models. A system message does not take effect for QVQ models.
Properties
content string (Required)
The content of the message.
role string (Required)
The role for the system message. The value is fixed to system.
User Message object (Required)
A user message that is used to pass questions, instructions, or context to the model.
Properties
content string or array (Required)
The content of the message. If the input is only text, this parameter is a string. If the input includes multimodal data, such as images, or if explicit caching is enabled, this parameter is an array.
Properties
text string (Required)
The input text.
image string (Optional)
The image file for image understanding. You can pass an image in one of the following three ways:
-
Public URL: A publicly accessible image link.
-
Base64 encoding of the image, in the format data:image/<format>;base64,<data>.
-
Local file: The absolute path of a local file.
Applicable models: Qwen-VL, QVQ
Example: {"image":"https://xxxx.jpeg"}
video array or string (Optional)
The video to pass when you use a Qwen-VL model or a QVQ model.
-
If you pass an image list, the type is array.
-
If you pass a video file, the type is string.
To pass a local file, see Local file (Qwen-VL) or Local file (QVQ).
Examples:
-
Image list: {"video":["https://xx1.jpg",...,"https://xxn.jpg"]}
-
Video file: {"video":"https://xxx.mp4"}
fps float (Optional)
The number of frames to extract per second. The value must be in the range of [0.1, 10]. The default value is 2.0.
Description
The `fps` parameter has two functions:
-
When a video file is the input, this parameter controls the frame extraction frequency. One frame is extracted every fps1 seconds.
This applies to Qwen-VL models and QVQ models.
-
It informs the model of the time interval between adjacent frames, which helps the model better understand the video's temporal dynamics. This applies to both video file and image list inputs. This feature is suitable for scenarios such as event time localization or summarizing content by segment.
This is supported by Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL, Qwen2.5-VL, and QVQ models.
A larger fps value is suitable for high-speed motion scenarios, such as sports events and action movies. A smaller fps value is suitable for long videos or scenarios with relatively static content.
Examples
-
Passing an image list: {"video":["https://xx1.jpg",...,"https://xxn.jpg"],"fps":2}
-
Passing a video file: {"video": "https://xx1.mp4","fps":2}
max_frames integer (Optional)
The maximum number of frames that can be extracted from a video. If the number of frames calculated based on fps exceeds max_frames, the system automatically adjusts to extract frames uniformly within the max_frames limit. This ensures that the total number of frames does not exceed the limit.
Value range
-
qwen3.7 series, qwen3.6 series, qwen3.5 series: The maximum and default value is 8000.
-
qwen3-vl-plus series, qwen3-vl-flash series, qwen3-vl-235b-a22b-thinking, qwen3-vl-235b-a22b-instruct: The maximum and default value is 2000.
-
qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, qwen-vl-plus-0710: The maximum and default value is 512.
Sample value
{"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"max_frame": 2000}
When you call with an OpenAI-compatible API, you cannot customize the max_frames parameter. The API automatically uses the default value for each model.
min_pixels integer (Optional)
Sets the minimum pixel threshold for the input image or video frames. If the total pixels of an input image or video frame are less than min_pixels, the image or frame is enlarged until its total pixels are higher than min_pixels.
Examples
-
Image input: {"type": "image_url","image_url": {"url":"https://xxxx.jpg"},"min_pixels": 65536}
-
Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"min_pixels": 65536}
-
Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"min_pixels": 65536}
max_pixels integer (Optional)
Sets the maximum pixel threshold for the input image or video frames. If the total pixels of an input image or video are within the [min_pixels, max_pixels] range, the model recognizes the original image. If the total pixels of the input image are greater than max_pixels, the image is scaled down until the total pixels are below max_pixels.
Examples
-
Image input: {"type": "image_url","image_url": {"url":"https://xxxx.jpg"},"max_pixels": 8388608}
-
Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"max_pixels": 655360}
-
Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"max_pixels": 655360}
total_pixels integer (Optional)
Limits the total pixels of all frames that are extracted from a video (pixels of a single frame × total number of frames). If the total pixels of the video exceed this limit, the system scales down the video frames but still ensures that the pixel value of a single frame is within the [min_pixels, max_pixels] range. This applies to Qwen-VL and QVQ models.
For long videos with many extracted frames, you can appropriately lower this value to reduce token consumption and processing time, but this may result in the loss of image details.
Value range
-
qwen3.7 series, qwen3.6 series, qwen3.5 series: The default and maximum value is 819200000. This value corresponds to 800000 image tokens (1 image token per 32×32 pixels).
-
qwen3-vl-plus series, qwen3-vl-flash series, qwen3-vl-235b-a22b-thinking, qwen3-vl-235b-a22b-instruct: The default and maximum value is 134217728. This value corresponds to 131072 image tokens (1 image token per 32×32 pixels).
-
Other Qwen3-VL open source models, qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, qwen-vl-plus-0710: The default and minimum value is 67108864. This value corresponds to 65536 image tokens (1 image token per 32×32 pixels).
-
Other qwen-vl-plus models, other qwen-vl-max models, Qwen2.5-VL open source series, and QVQ series models: The default and minimum value is 51380224. This value corresponds to 65536 image tokens (1 image token per 28×28 pixels).
Examples
-
Video file input: {"type": "video_url","video_url": {"url":"https://xxxx.mp4"},"total_pixels": 134217728}
-
Image list input: {"type": "video","video": ["https://xx1.jpg",...,"https://xxn.jpg"],"total_pixels": 134217728}
audio string
This is a required parameter for audio understanding models, such as qwen-audio-turbo.
The audio file to pass when you use the audio understanding feature.
Example: {"audio":"https://xxx.mp3"}
cache_control object (Optional)
This is supported only by models that support explicit caching. It is used to enable explicit caching.
Properties
type string (Required)
The value must be ephemeral.
role string (Required)
The role for a user message. The value must be user.
Assistant Message object (Optional)
The model's reply to the user message.
Properties
content string (Optional)
The content of the message. This is optional only if the tool_calls parameter is specified in the assistant message.
role string (Required)
The value must be assistant.
partial boolean (Optional)
Specifies whether to enable partial mode. For more information and a list of supported models, see Partial mode.
tool_calls array (Optional)
The tool and input parameter information that is returned after you initiate a function call. It contains one or more objects. This is obtained from the tool_calls field of the previous model response.
Properties
id string
The ID of the tool response.
type string
The tool type. Currently, only function is supported.
function object
The tool and input parameter information.
Properties
name string
The tool name.
arguments string
The input parameter information, in JSON string format.
index integer
The index of the current tool information in the tool_calls array.
Tool Message object (Optional)
The output information of the tool.
Properties
content string (Required)
The output content of the tool function. It must be in string format.
role string (Required)
The value must be tool.
tool_call_id string (Optional)
The ID that is returned after you initiate a function call. You can retrieve it using response.output.choices[0].message.tool_calls[$index]["id"]. It is used to mark the tool that corresponds to the tool message.
|
|
temperature float (Optional)
The sampling temperature, which controls the diversity of the text that is generated by the model.
A higher temperature results in more diverse text, and a lower temperature results in more deterministic text.
Value range: [0, 2)
Default temperature values
-
qwen3.8-max: Defaults to 0.6; values below 0.6 will be automatically reset to 0.6.
-
Qwen3.7 (non-thinking mode), Qwen3.6 (non-thinking mode), Qwen3.5-Omni, Qwen3.5 (non-thinking mode), Qwen3 (non-thinking mode), Qwen3-Instruct series, Qwen3-Coder series, qwen-max series, qwen-plus series (non-thinking mode), qwen-flash series (non-thinking mode), qwen-turbo series (non-thinking mode), qwen open source series, qwen-coder series, qwen-doc-turbo, Qwen3-VL (non-thinking): 0.7;
-
QVQ series: 0.5;
-
qwen-audio-turbo series: 0.00001;
-
qwen-vl series, qwen2.5-omni-7b: 0.01;
-
qwen-math series: 0;
-
Qwen3.7 (thinking mode), Qwen3.6 (thinking mode), Qwen3.5 (thinking mode), Qwen3 (thinking mode), Qwen3-Thinking, Qwen3-Omni-Captioner, QwQ series: 0.6;
-
qwen3-max-preview (thinking mode), qwen-long series: 1.0;
-
qwen-plus-character: 0.92
-
qwen3-omni-flash series: 0.9
-
Qwen3-VL (thinking mode): 0.8
-
DeepSeek series (supplied by Alibaba Cloud): deepseek-v4-pro, deepseek-v4-flash, deepseek-v3.2 (non-thinking mode): 1.0; deepseek-v3.2 (thinking mode), deepseek-v3.2-exp, deepseek-v3.1, deepseek-r1, deepseek-r1-0528, deepseek-r1-distill-qwen distilled version: 0.6; deepseek-v3: 0.7;
-
DeepSeek series (supplied by SiliconFlow): siliconflow/deepseek-v3.2, siliconflow/deepseek-v3.1-terminus, siliconflow/deepseek-r1-0528, siliconflow/deepseek-v3-0324: 1.0;
-
DeepSeek series (supplied by Vanchin): vanchin/deepseek-v3.2-think (thinking mode): 0.6; vanchin/deepseek-v3.1-terminus: 0.7; vanchin/deepseek-v3.2-speciale, vanchin/deepseek-r1, vanchin/deepseek-v3, vanchin/deepseek-ocr: 1.0;
-
Kimi series (supplied by Alibaba Cloud): kimi-k2.7-code, kimi-k2.6 (thinking mode), kimi-k2.5 (thinking mode), kimi-k2-thinking: 1.0; kimi-k2.6 (non-thinking mode), kimi-k2.5 (non-thinking mode), Moonshot-Kimi-K2-Instruct: 0.6;
-
Kimi series (supplied by Moonshot AI): kimi/kimi-k3, kimi/kimi-k2.7-code-highspeed, kimi/kimi-k2.7-code, kimi/kimi-k2.6 (thinking mode), kimi/kimi-k2.5 (thinking mode): 1.0; kimi/kimi-k2.6 (non-thinking mode), kimi/kimi-k2.5 (non-thinking mode): 0.6;
-
GLM series (supplied by Alibaba Cloud): glm-5.1, glm-5, glm-4.7, glm-4.6: 1.0; glm-4.5, glm-4.5-air: 0.6;
-
GLM series (supplied by ZHIPU AI): ZHIPU/GLM-5.1, ZHIPU/GLM-5: 0.6;
-
MiniMax series (supplied by Alibaba Cloud): MiniMax-M2.5, MiniMax-M2.1: 1.0;
-
MiniMax series (provided directly by MiniMax): MiniMax/MiniMax-M3, MiniMax/MiniMax-M2.7, MiniMax/MiniMax-M2.5, and MiniMax/MiniMax-M2.1 (Version 1.0).
-
MiMo series (supplied by Xiaomi): mimo-v2.5-pro: 1.0, range [0, 1.5].
When you call over HTTP, place temperature in the parameters object.
We do not recommend that you modify the default temperature value for QVQ models.
|
|
top_p float (Optional)
The probability threshold for nucleus sampling, which controls the diversity of the text that is generated by the model.
A higher `top_p` value results in more diverse text, and a lower `top_p` value results in more deterministic text.
Value range: (0, 1.0].
Default top_p values
Qwen3.8 (non-thinking mode), Qwen3.7 (non-thinking mode), Qwen3.6 (non-thinking mode), Qwen3.5-Omni, Qwen3.5 (non-thinking mode), Qwen3 (non-thinking mode), Qwen3-Instruct series, Qwen3-Coder series, qwen-max series, qwen-plus series (non-thinking mode), qwen-flash series (non-thinking mode), qwen-turbo series (non-thinking mode), Qwen 2.5 open source series, qwen-coder series, qwen-long, qwen-doc-turbo, Qwen3-VL (non-thinking): 0.8;
qwen-omni-turbo series: 0.01;
qwen-vl-plus series, qwen-vl-max, qwen2.5-omni-7b: 0.001;
QVQ series: 0.5;
qwen3-max-preview (thinking mode), qwen-math series, Qwen3-Omni-Flash series: 1.0;
Qwen3.8 (thinking mode), Qwen3.7 (thinking mode), Qwen3.6 (thinking mode), Qwen3.5 (thinking mode), Qwen3 (thinking mode), Qwen3-VL (thinking mode), Qwen3-Thinking, QwQ series, Qwen3-Omni-Captioner, qwen-plus-character: 0.95
DeepSeek series (supplied by Alibaba Cloud): deepseek-v4-pro, deepseek-v4-flash, deepseek-v3.2, deepseek-v3.2-exp, deepseek-v3.1, deepseek-r1, deepseek-r1-0528, deepseek-r1-distill-qwen distilled version: 0.95; deepseek-v3: 0.6;
DeepSeek series (supplied by SiliconFlow): siliconflow/deepseek-v3.2, siliconflow/deepseek-v3.1-terminus, siliconflow/deepseek-r1-0528, siliconflow/deepseek-v3-0324: 1.0;
DeepSeek series (supplied by Vanchin): vanchin/deepseek-v3.2-think, vanchin/deepseek-v3.1-terminus: 0.95; vanchin/deepseek-v3.2-speciale: 0.9; vanchin/deepseek-r1: 0.8; vanchin/deepseek-v3, vanchin/deepseek-ocr: 1.0;
Kimi series (supplied by Alibaba Cloud): kimi-k2.7-code, kimi-k2.6, kimi-k2.5, kimi-k2-thinking: 0.95; Moonshot-Kimi-K2-Instruct: 1.0;
Kimi series (supplied by Moonshot AI): kimi/kimi-k3, kimi/kimi-k2.7-code-highspeed, kimi/kimi-k2.7-code, kimi/kimi-k2.6, kimi/kimi-k2.5: 0.95;
GLM series (supplied by Alibaba Cloud): 0.95;
GLM series (supplied by ZHIPU AI): ZHIPU/GLM-5.1, ZHIPU/GLM-5: 0.95;
MiniMax series (supplied by Alibaba Cloud): MiniMax-M2.5, MiniMax-M2.1: 0.95;
MiniMax series (supplied by MiniMax): MiniMax/MiniMax-M3: 0.95; MiniMax/MiniMax-M2.7, MiniMax/MiniMax-M2.5, MiniMax/MiniMax-M2.1: 0.9.
MiMo series (supplied by Xiaomi): xiaomi/mimo-v2.5-pro: 0.95, range [0.01, 1.0].
In the Java SDK, this parameter is topP. When you call over HTTP, place top_p in the parameters object.
We do not recommend that you modify the default `top_p` value for QVQ models.
|
|
top_k integer (Optional)
The size of the candidate set for sampling during generation. For example, if you set this parameter to 50, only the 50 tokens with the highest scores in a single generation are used to form the candidate set for random sampling. A larger value increases randomness, and a smaller value increases determinism. A value of `None` or a value greater than 100 indicates that the `top_k` strategy is not enabled and only the `top_p` strategy takes effect.
The value must be greater than or equal to 0.
Default top_k values
QVQ series: 10
QwQ series: 40
qwen-math series, models before the rest of the qwen-vl-plus series, qwen-audio-turbo series, : 1
All other models: 20
GLM series (provided by Alibaba Cloud): 20
DeepSeek, Kimi, and MiniMax series do not support the `top_k` parameter.
In the Java SDK, this parameter is topK. When you call over HTTP, place top_k in the parameters object.
We do not recommend that you modify the default `top_k` value for QVQ models.
|
|
enable_thinking boolean (Optional)
Specifies whether to enable thinking mode for a hybrid thinking model. This applies to Qwen3.7, Qwen3.6, Qwen3.5, Qwen3, and Qwen3-VL models, along with the DeepSeek-V4-Pro/V4-Flash series (provided by Alibaba Cloud), DeepSeek-V3.2/V3.2-exp/V3.1 series (provided by Alibaba Cloud and SiliconFlow), Kimi-K2.6/K2.5 series (provided by Alibaba Cloud), and GLM series. The DeepSeek-V4 series has thinking mode enabled by default. You can adjust the inference effort with the reasoning_effort parameter.
Valid values:
For the default values for different models, see Supported models.
In the Java SDK, this parameter is `enableThinking`. When you call over HTTP, place enable_thinking in the parameters object.
|
|
preserve_thinking boolean (Optional) The default value is false. (Default value for qwen3.8-max: true)
Specifies whether to append the reasoning_content from assistant messages in the conversation history to the model input. This is suitable for scenarios where the model needs to refer to the historical thinking process.
Currently supported by qwen3.7-max, qwen3.7-max-2026-05-20 and subsequent snapshots, qwen3.6-max-preview, qwen3.7-plus, qwen3.7-plus-2026-05-26, qwen3.6-plus, qwen3.6-plus-2026-04-02, qwen3.7-flash, qwen3.7-flash-2026-07-15, qwen3.6-flash, qwen3.6-flash-2026-04-16, qwen3.8-max (enabled by default), kimi-k2.6 (deployed on Alibaba Cloud Model Studio), kimi-k2.7-code (deployed on Alibaba Cloud Model Studio, enabled by default), kimi/kimi-k2.7-code-highspeed (supplied by Moonshot AI, enabled by default), and kimi/kimi-k2.7-code (supplied by Moonshot AI, enabled by default).
Important (qwen3.8-max): When using qwen3.8-max, preserve_thinking defaults to true. You must send back all historical reasoning_content in the reasoning_content field. Do NOT concatenate reasoning_content into the content field. Doing so may degrade model performance.
-
If the historical messages do not contain reasoning_content, enabling this parameter does not cause an error.
-
When enabled, the reasoning_content from the historical conversation is included in the input token count and is billed.
When you call over HTTP, place preserve_thinking in the parameters object. The Java SDK is not supported.
|
|
thinking_budget integer (Optional)
The maximum length of the thinking process. This applies to Qwen3.8, Qwen3.7, Qwen3.6, Qwen3.5, Qwen3-VL, Qwen3, GLM(supplied by Alibaba Cloud) and Kimi(supplied by Alibaba Cloud) models. For more information, see Limit thinking length.
The default value is the maximum chain-of-thought length for the model. For more information, see Select a model.
In the Java SDK, this parameter is `thinkingBudget`. When you call over HTTP, place thinking_budget in the parameters object.
The default value is the maximum chain-of-thought length for the model.
|
|
reasoning_effort string (Optional)
Controls the inference intensity of models. The valid values and default values vary by model.
DeepSeek-V4 and GLM series (Default value: high)
Valid values: high (high-intensity inference) and max (maximum-intensity inference). `low` and `medium` are mapped to `high`, and `xhigh` is mapped to `max`.
This applies to glm-5.2, glm-5.1, glm-5, deepseek-v4-pro, and deepseek-v4-flash (provided by Alibaba Cloud).
qwen3.8-max: Default value: xhigh
Valid values:
-
xhigh (default): Maximum-intensity inference
-
medium: Standard inference
-
low: Low-intensity inference
OpenAI standard value mapping: max is mapped to xhigh, high is mapped to xhigh, minimal is mapped to low, and none is mapped to enable_thinking=False.
Setting values other than the above valid values and mapped values will cause an error.
For qwen3.8-max, reasoning_effort and thinking_budget cannot be set at the same time. Setting both will cause an error. However, they support mutual conversion:
-
When thinking_budget is not set, the reasoning_effort levels are automatically mapped to thinking_budget: low corresponds to 4096, medium corresponds to 16384, and xhigh corresponds to 262144.
-
When reasoning_effort is not set, thinking_budget is automatically mapped back to reasoning_effort: 0–4096 corresponds to low, 4097–16384 corresponds to medium, and 16385–262144 corresponds to xhigh.
-
When neither is set, the default thinking_budget (131072) and default reasoning_effort (xhigh) are used.
When you call over HTTP, place reasoning_effort in the parameters object.
|
|
tool_stream boolean (Optional) The default value is false.
This parameter only affects the streaming output behavior of complex tool parameters and is effective only in streaming calls. Simple tool parameters, where all parameter types are strings, can be streamed as long as streaming calls are enabled. tool_stream has no effect on them. Complex tools are tools where some parameter types in the tool definition are arrays or objects. Currently, only the Qwen and GLM series support this.
Qwen series support list:
Qwen series usage reference:
Complex tools are tools where some parameter types in the tool definition are arrays or objects.
GLM series support list: glm-4.6, glm-4.7, glm-5, and glm-5.1 (provided by Alibaba Cloud).
GLM series usage reference:
When you call over HTTP, place tool_stream in the parameters object.
|
|
enable_code_interpreter boolean (Optional) The default value is false.
Specifies whether to enable the code interpreter feature. For more information, see Code interpreter.
Valid values:
The Java SDK is not supported. When you call over HTTP, place enable_code_interpreter in the parameters object.
|
|
clear_thinking boolean (Optional) The default value is `false`.
Controls whether to use the reasoning_content (thinking process) from previous turns as context input for the model in a multi-turn conversation. This is supported only by the GLM series models glm-5.2, glm-5.1, glm-5, and glm-4.7.
-
true: Enables the feature. This ignores the reasoning_content from previous turns and uses only visible text, tool calls, and results as context input. This can reduce context length and cost.
-
false (default): Disables the feature. This retains the reasoning_content from previous turns and provides it to the model along with the context. If you want to enable preserved thinking, you must pass the historical reasoning_content completely, unmodified, and in its original order in the messages. Missing, trimming, rewriting, or reordering degrades performance or prevents the feature from taking effect.
|
|
repetition_penalty float (Optional)
The penalty for repeating consecutive sequences during model generation. A higher `repetition_penalty` value can reduce repetition in the model's output. A value of 1.0 indicates no penalty. The value must be greater than 0.
Default repetition_penalty values
-
qwen-max, qwen-math series, qwen-vl-max series, qwen-audio-turbo series, QVQ series, QwQ series, Qwen3-VL: 1.0
-
qwen-coder series: 1.1
-
qwen-vl-plus: 1.2
-
All other models: 1.05
-
DeepSeek series (provided by Alibaba Cloud): deepseek-v3.2-exp/v3.1: 1.0
-
GLM series (provided by Alibaba Cloud): 1.0
In the Java SDK, this parameter is repetitionPenalty. When you call over HTTP, place repetition_penalty in the parameters object.
When you use the qwen-vl-plus_2025-01-25 model for text extraction, we recommend that you set `repetition_penalty` to 1.0.
We do not recommend that you modify the default `repetition_penalty` value for QVQ models.
|
|
presence_penalty float (Optional)
Controls the content repetition when the model generates text.
Value range: [-2.0, 2.0]. Positive values reduce repetition, while negative values increase it.
In scenarios that require diversity, fun, or creativity, such as creative writing or brainstorming, you can increase this value. In scenarios that emphasize consistency and term accuracy, such as technical documents or formal texts, you can decrease this value.
Default presence_penalty values
Qwen3.7 (non-thinking mode), Qwen3.6 (non-thinking mode), Qwen3.5-Omni, Qwen3.5 (non-thinking mode), qwen3-max-preview (thinking mode), Qwen3 (non-thinking mode), Qwen3-Instruct series/1.7b/4b (thinking mode), QVQ series, qwen-max, qwen2.5-vl series, qwen-vl-max series, qwen-vl-plus, Qwen3-VL (non-thinking): 1.5;
qwen3-8b/14b/32b/30b-a3b/235b-a22b (thinking mode), qwen-plus/qwen-plus-latest/2025-04-28 (thinking mode), qwen-turbo/qwen-turbo/2025-04-28 (thinking mode): 0.5;
All others are 0.0.
DeepSeek series (supplied by Alibaba Cloud): deepseek-r1, deepseek-r1-0528, deepseek-r1-distill-qwen distilled version: 1;
Kimi series (supplied by Alibaba Cloud): kimi-k2.7-code, kimi-k2.6, kimi-k2.5: 0.0;
Kimi series (supplied by Moonshot AI): 0.0;
MiniMax series (supplied by Alibaba Cloud): MiniMax-M2.5, MiniMax-M2.1: 0.0;
Other DeepSeek, Kimi, GLM, and MiniMax models have no default value.
How it works
If the parameter value is positive, the model applies a penalty to tokens that already exist in the text. The penalty is not related to the number of times the token appears. This reduces the likelihood of these tokens reappearing, thus reducing content repetition and increasing word diversity.
Example
Prompt: Translate this sentence into Chinese: "This movie is good. The plot is good, the acting is good, the music is good, and overall, the whole movie is just good. It is really good, in fact. The plot is so good, and the acting is so good, and the music is so good."
Parameter value 2.0: This movie is great. The plot is fantastic, the acting is superb, and the music is also very beautiful. Overall, the entire film is just incredible. It is actually truly outstanding. The storyline is very exciting, the performances are excellent, and the soundtrack is so moving.
Parameter value 0.0: This movie is good. The plot is good, the acting is good, and the music is good. Overall, the whole movie is very good. In fact, it is really great. The plot is very good, the acting is also very excellent, and the music is equally outstanding.
Parameter value -2.0: This movie is good. The plot is good, the acting is good, and the music is good. Overall, the whole movie is good. In fact, it is really good. The plot is very good, the acting is very good, and the music is very good.
When you use the qwen-vl-plus model for text extraction, set presence_penalty to 1.5.
Do not modify the default presence_penalty value for QVQ models.
The Java SDK does not support setting this parameter. When you call over HTTP, place presence_penalty in the parameters object.
|
|
vl_high_resolution_images boolean (Optional) Default value: false
Specifies whether to increase the pixel limit for input images to the pixel count that corresponds to 16384 tokens. For more information, see Processing high-resolution images.
-
vl_high_resolution_images: true uses a fixed resolution strategy and ignores the max_pixels setting. If the resolution is exceeded, the total pixel count of the image is scaled down to stay within this limit.
Click to view the pixel limits for each model
When vl_high_resolution_images is True, the pixel limits vary by model:
-
For the Qwen3.8 series, Qwen3.7 series, Qwen3.6 series, Qwen3.5 series, Qwen3-VL series, qwen-vl-max, qwen-vl-max-0813, qwen-vl-plus, qwen-vl-plus-0815, and qwen-vl-plus-0710 models, the value is 16777216. (Each Token corresponds to 32*32 pixels. The total value is calculated as 16384*32*32.)
-
QVQ series, other Qwen2.5-VL series models: 12845056 (1 token corresponds to 28*28 pixels, which is 16384*28*28)
-
vl_high_resolution_images is false, the pixel limit is determined by max_pixels. If the input image's pixel count exceeds max_pixels, the image is scaled down to within the max_pixels limit. The default pixel limit for each model is the default value of max_pixels.
In the Java SDK, this parameter is vlHighResolutionImages (requires V2.20.8 or later). When you call over HTTP, place vl_high_resolution_images in the parameters object.
|
|
vl_enable_image_hw_output boolean (Optional) The default value is false.
Specifies whether to return the dimensions of the scaled image. The model scales the input image. If you set this parameter to `True`, it returns the height and width of the scaled image. If streaming output is enabled, this information is returned in the last chunk. This is supported by Qwen-VL models.
In the Java SDK, this parameter is vlEnableImageHwOutput. The minimum required Java SDK version is 2.20.8. When you call over HTTP, place vl_enable_image_hw_output in the parameters object.
|
|
max_tokens integer (Optional, to be deprecated)
This parameter will be deprecated. For new integrations, use max_completion_tokens.
The maximum length of the model's answer, which excludes chain-of-thought content. That is: Model answer = Model output – Chain-of-thought (if any).
The default and maximum values are both the model's maximum output length.
If the model's answer exceeds this value, generation stops early, and the returned finish_reason is length.
For GLM-5.2 and later GLM series models, max_tokens behaves the same as max_completion_tokens — it limits the total output length including the chain-of-thought, not just the final response. We recommend using the max_completion_tokens parameter directly with GLM-5.2 series models for more semantically explicit control.
In the Java SDK, this parameter is maxTokens. For Qwen-VL/Audio models, it is maxLength in the Java SDK, but versions later than 2.18.4 also support setting it as `maxTokens`. When you call over HTTP, place max_tokens in the parameters object.
|
|
max_completion_tokens integer (Optional)
The maximum length of the model's output, including the chain-of-thought and the model's answer. If the model's output exceeds this value, generation stops early, and the returned finish_reason is length.
The default and maximum values are both the model's maximum output length.
Difference from max_tokens: max_completion_tokens limits the complete model output (chain-of-thought + answer), while max_tokens only limits the answer part. For thinking models, we recommend that you use max_completion_tokens.
The following models are supported:
-
Qwen Max: Qwen3.7-Max and later models
-
Qwen Plus: Qwen3.5-Plus and later models
-
Qwen Flash: Qwen3.5-Flash and later models
-
Kimi: kimi-k2.5 and later models
-
GLM: glm-5 and later models
-
MiniMax: MiniMax-M2.5 and later models
-
DeepSeek: deepseek-v3, deepseek-r1, deepseek-r1-0528, deepseek-v3.1, deepseek-v3.2, deepseek-v3.2-exp, deepseek-v4-pro, deepseek-v4-flash, and later models
The models listed above do not include models supplied directly by third parties.
There may be a difference of up to 10 tokens between the actual output token count and the specified max_completion_tokens value.
The Java SDK does not currently support this parameter. When you call over HTTP, place max_completion_tokens in the parameters object.
|
|
seed integer (Optional)
A random number seed. This parameter is used to ensure reproducible results with the same input and parameters. If you pass the same seed value in a call and other parameters remain unchanged, the model returns the same result as much as possible.
Value range: [0,2<sup>31</sup>−1].
Default seed values
qwen-vl-max, qvq-max series: 3407;
qwen-vl-max-2024-02-01, qwen-vl-plus: No default value;
All other models: 1234.
When you call over HTTP, place seed in the parameters object.
|
|
stream boolean (Optional) The default value is false.
Specifies whether to stream the reply. The valid values are:
-
false: The model generates all content and then returns the result at once.
-
true: The model generates and outputs content on the fly. This means that the model immediately outputs a chunk of content as soon as it is generated.
This parameter is supported only by the Python SDK. To implement streaming output with the Java SDK, call the streamCall interface. To implement streaming output over HTTP, specify X-DashScope-SSE as enable in the header.
Qwen3 commercial edition (thinking mode), Qwen3 open source edition, QwQ, and QVQ support only streaming output.
|
|
incremental_output boolean (Optional) The default is false. For Qwen3-Max, Qwen3-VL, Qwen3 open source edition, QwQ, and QVQ models, the default is true.
Specifies whether to enable incremental output in streaming output mode. We recommend that you set this parameter to true.
Value:
-
false: Each output contains the entire sequence that is generated so far. The last output is the complete generated result. I
I like
I like apple
I like apple.
-
true (recommended): The output is incremental. Subsequent output does not include previously output content. You must read these chunks one by one in real time to obtain the complete result. I
like
apple
.
In the Java SDK, this parameter is incrementalOutput. When you call over HTTP, place incremental_output in the parameters object.
QwQ models and Qwen3 models in thinking mode support only setting this parameter to true. Because the default value for Qwen3 commercial edition models is false, you must manually set it to true in thinking mode.
Qwen3 open source edition models do not support setting this parameter to false.
|
|
response_format object (Optional) The default value is {"type": "text"}.
The format of the returned content. The valid values are:
For more information, see Structured output.
For a list of supported models, see Supported models.
If you specify {"type": "json_object"}, you must explicitly instruct the model to output JSON in the prompt, such as "Please output in JSON format". Otherwise, an error occurs.
In the Java SDK, this parameter is `responseFormat`. When you call over HTTP, place response_format in the parameters object.
Properties
type string (Required)
The format of the returned content. The valid values are:
|
|
result_format string (Optional) The default is text. For Qwen3-Max, Qwen3-VL, QwQ models, Qwen3 open source models (except qwen3-next-80b-a3b-instruct) and Qwen-Long models, the default is `message`.
The format of the returned data. We recommend that you set this parameter to message to facilitate multi-turn conversations.
The platform will later unify the default value to message.
In the Java SDK, this parameter is resultFormat. When you call over HTTP, place result_format in the parameters object.
If the model is Qwen-VL, QVQ, or Audio, setting the value to text has no effect.
Qwen3-Max, Qwen3-VL, and Qwen3 models in thinking mode can only be set to message. Because the default value for Qwen3 commercial edition models is text, you need to set it to message.
If you use the Java SDK to call a Qwen3 open source model and pass text, the response is still returned in message format.
|
|
logprobs boolean (Optional) The default value is false.
Specifies whether to return the log probabilities of the output tokens. The valid values are:
-
true
Back
-
false
You cannot return.
The following models are supported:
-
Snapshot models of the qwen-plus series (excluding stable edition models)
-
Snapshot models of the qwen-turbo series (excluding stable edition models)
-
qwen3-vl-plus series (including stable edition models)
-
qwen3-vl-flash series (including stable edition models)
-
Qwen3 open source models
When you call over HTTP, place logprobs in the parameters object.
|
|
top_logprobs integer (Optional) The default value is 0.
Specifies the number of most likely candidate tokens to return at each generation step.
Value range: [0, 5]
This parameter takes effect only if logprobs is true.
In the Java SDK, this parameter is topLogprobs. When you call over HTTP, place top_logprobs in the parameters object.
|
|
n integer (Optional) The default value is 1.
The number of responses to generate. The value range is 1-4. For scenarios that require multiple responses to be generated, such as creative writing or ad copy, you can set a larger `n` value.
Currently, only Qwen3 (non-thinking mode) and qwen-plus-character models are supported. The value is fixed at 1 if the `tools` parameter is passed.
Setting a larger `n` value does not increase input token consumption but does increase output token consumption.
When you call over HTTP, place n in the parameters object.
|
|
stop string or array (Optional)
Used to specify stop words. When a string or token_id specified in stop appears in the generated text, generation stops immediately.
You can pass sensitive words to control the model's output.
When stop is an array, you cannot input both token_id and strings as elements. For example, you cannot specify ["Hello",104307].
When you call over HTTP, place stop in the parameters object.
|
|
tools array (Optional)
An array that contains one or more tool objects for the model to call during function calling. For more information, see Function Calling.
When you use tools, you must set result_format to message.
When you initiate function calling or submit tool execution results, you must set the tools parameter.
Properties
type string (Required)
The tool type. Currently, only function is supported.
function object (Required)
Properties
name string (Required)
The name of the tool function. It must consist of letters and numbers, and can contain underscores and hyphens. The maximum length is 64 characters.
description string (Required)
A description of the tool function, which helps the model to choose when and how to call the tool function.
parameters object (Optional) The default value is {}.
A description of the tool's parameters, which needs to be a valid JSON Schema. For a description of JSON Schema, see this link. If the parameters parameter is empty, it means the tool has no input parameters, such as a time query tool.
To improve the accuracy of tool calls, we recommend that you pass parameters.
When you call over HTTP, place tools in the parameters object. This is temporarily not supported for qwen-vl and qwen-audio series models.
|
|
tool_choice string or object (Optional) The default value is auto.
The tool selection strategy. You can set this parameter to force a tool call method for a specific type of problem, such as always using a certain tool or disabling all tools.
-
auto
The LLM chooses the tool strategy autonomously.
-
none
If you want to temporarily disable tool calls in a specific request, you can set the tool_choice parameter to none.
-
{"type": "function", "function": {"name": "the_function_to_call"}}
If you want to force a call to a specific tool, you can set the tool_choice parameter to {"type": "function", "function": {"name": "the_function_to_call"}}, where the_function_to_call is the name of the specified tool function.
Models in thinking mode do not support forcing a call to a specific tool.
In the Java SDK, this parameter is toolChoice. When you call over HTTP, place tool_choice in the parameters object.
|
|
parallel_tool_calls boolean (Optional) The default value is false.
Specifies whether to enable parallel tool calls.
Valid values:
-
true: Enabled
-
false: Disabled.
For more information about parallel tool calls, see Parallel tool calls.
In the Java SDK, this parameter is parallelToolCalls. When you call over HTTP, place parallel_tool_calls in the parameters object.
|
|
enable_search boolean (Optional) The default value is false.
Specifies whether the model uses Internet search results as a reference when it generates text. The valid values are:
-
true: Enables Internet search. The model uses search results as reference information during text generation, but the model decides whether to use the Internet search results based on its internal logic.
If web search is not performed after enabling, you can optimize the prompt or set the forced_search parameter in search_options to enable forced search.
-
false: Disables Internet search.
For billing information, see Billing.
In the Java SDK, this parameter is enableSearch. When you call over HTTP, place enable_search in the parameters object.
Enabling the Internet search feature may increase token consumption.
|
|
search_options object (Optional)
The policy for web search. This parameter takes effect only if enable_search is true. For more information, see Web search.
When you call over HTTP, place search_options in the parameters object. In the Java SDK, this parameter is searchOptions.
Properties
enable_source boolean (Optional) The default value is false.
Specifies whether to display the searched information in the returned result. The valid values are:
enable_citation boolean (Optional) The default value is false.
Specifies whether to enable the superscript annotation feature in the style of [1] or [ref_1]. This takes effect if enable_source is true. The valid values are:
citation_format string (Optional) The default value is "[<number>]".
The style of the superscript. This takes effect if enable_citation is true. The valid values are:
forced_search boolean (Optional) The default value is false.
Specifies whether to force search. The valid values are:
search_strategy string (Optional) The default value is turbo.
The strategy for searching Internet information.
The valid values are:
-
turbo (default): Balances response speed and search effectiveness and is suitable for most scenarios.
-
max: Adopts a more comprehensive search strategy and can call multiple search engine sources to obtain more detailed search results, but the response time may be longer.
-
agent: Can call the web search tool and the LLM multiple times to achieve multi-round information retrieval and content integration.
This strategy is applicable only to qwen3.8-max, qwen3.7-max, qwen3.7-max-2026-05-20, qwen3.5-plus, qwen3.5-plus-2026-02-15, qwen3.5-flash, qwen3.5-flash-2026-02-23, qwen3-max and qwen3-max-2026-01-23 in thinking mode (streaming only), and qwen3-max-2026-01-23 in non-thinking mode, qwen3-max-2025-09-23.
If this strategy is enabled, only returning search sources (enable_source: true) is supported. Other web search features are not available.
-
agent_max: Supports web scraping on top of the agent strategy. For more information, see Web scraping.
This strategy is applicable only to qwen3.8-max, qwen3.7-max, qwen3.7-max-2026-05-20, qwen3-max, and qwen3-max-2026-01-23 in thinking mode.
If this strategy is enabled, only returning search sources (enable_source: true) is supported. Other web search features are not available.
enable_search_extension boolean (Optional) The default value is false.
Specifies whether to enable domain-specific enhancement. The valid values are:
-
true
Enabled.
-
false (default)
Disabled.
prepend_search_result boolean (Optional) The default value is false.
In streaming output with enable_source set to true, you can use prepend_search_result to configure whether the first returned data packet contains only search source information. The valid values are:
The DashScope Java SDK is not currently supported.
|
|
X-DashScope-DataInspection string (Optional)
In addition to the content moderation capabilities of the Qwen API, this parameter specifies whether to further identify non-compliant information in the input and output content. The valid values are:
-
'{"input":"cip","output":"cip"}': Performs further detection.
-
Do not set this parameter: Does not further identify non-compliant information.
When you call over HTTP, place it in the request header: -H "X-DashScope-DataInspection: {\"input\": \"cip\", \"output\": \"cip\"}".
When you call with the Python SDK, configure it using headers: headers={'X-DashScope-DataInspection': '{"input":"cip","output":"cip"}'}.
For detailed usage, see Input and output AI safety guardrails.
This is not supported by the Java SDK.
This is not applicable to Qwen-Audio series models.
|
|
skill array (Optional)
The skill parameter, which is used to enable specific generation skills, such as PPT generation. Only the qwen-doc-turbo model supports this. For more information, see Generate a PPT.
When you call over HTTP, place skill in the parameters object.
When you use `skill`, stream must be set to true.
Properties
type string (Required)
The skill type. The currently supported value is:
mode string (Optional)
The PPT generation mode. The valid values are:
-
general (default): Template mode. This must be used with template_id to generate a PPT in HTML format.
-
creative: Creative mode. No template is required. This generates a graphic-based PPT where each page is an image.
template_id string (Optional)
The PPT template ID. This is used if mode is general or if mode is not set. The valid values are:
-
news_01: News template
-
summary_01: Summary template
-
internet_01: Internet template
-
thesis_01: Thesis template
|