更新时间：2026-07-29 GMT+08:00
多轮对话
chat.completions接口是无状态的，不会存储历史对话。为了实现多轮对话，模型需要在每次请求时，将历史信息都放在messages中，并通过role字段设置，让模型了解之前不同角色的不同对话内容（系统消息、用户消息、模型回复的消息），以便进行主题相关的延续性对话。
| 单轮对话 | 多轮对话 |
|---|---|
"messages":
[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "9.11和9.8哪个大？"}
] | "messages":
[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "9.11和9.8哪个大？"},
{"role": "assistant", "content": "9.8更大"},
{"role": "user", "content": "它们相加等于多少？"}
] |
API说明
模型调用的完整参数列表请见对话Chat/Post。
前提条件
- 已在页签开通预置服务。详情请见开通MaaS预置服务。
- （可选）如果需要控制服务调用流量，可提前创建自定义接入点，详情请参见创建自定义接入点。
- 已获取API Key。详情请见在MaaS管理API Key。
- 已获取模型服务的model参数值。支持的模型信息和接口详情请见对话Chat/Post。
快速入门
以下为多轮对话的示例代码，可通过model参数替换模型，model参数详情请参见文本生成。
思考模式下，reasoning_content是模型的思考内容，多轮对话场景下，不应作为输入。如果在输入的messages数组中包含此字段，将被忽略，不作为模型输入。进行多轮对话时，应只保留上一轮模型返回的role和content字段。
import requests
import json
if __name__ == '__main__':
url = "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions" # API地址
api_key = "MAAS_API_KEY" # 把MAAS_API_KEY替换成已获取的API Key
# Send request.
headers = {
'Content-Type': 'application/json',
'Authorization': f'Bearer {api_key}'
}
data = {
"model": "glm-5.2", # model参数
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "9.11和9.8哪个大？"},
{"role": "assistant", "content": "9.8更大"},
{"role": "user", "content": "它们相加等于多少？"}
]
}
response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
# Print result.
print(response.status_code)
print(response.text) 模型返回的content：
它们相加等于18.91。
curl -X POST "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MAAS_API_KEY" \
-d '{
"model": "glm-5.2",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "9.11和9.8哪个大？"},
{"role": "assistant", "content": "9.8更大"},
{"role": "user", "content": "它们相加等于多少？"}
]
}' 模型返回的content：
它们相加等于18.91。
建议JDK版本为15+。
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.time.Duration;
public class ChatCompletionsExample {
public static void main(String[] args) {
// 接口地址
String apiUrl = "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions";
// 把MAAS_API_KEY替换成已获取的API Key
String apiKey = "MAAS_API_KEY";
// 替换为你要调用的模型名称，例如 "deepseek-v3.2" 等
String modelName = "glm-5.2";
// 构造请求体
String requestBody = String.format(
"""
{
"model": "%s",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "9.11和9.8哪个大？"},
{"role": "assistant", "content": "9.8更大"},
{"role": "user", "content": "它们相加等于多少？"}
]
}""", modelName);
// 创建 HttpClient
HttpClient client = HttpClient.newBuilder()
.connectTimeout(Duration.ofSeconds(10))
.build();
// 创建请求
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(apiUrl))
.header("Content-Type", "application/json")
.header("Authorization", "Bearer " + apiKey)
.POST(HttpRequest.BodyPublishers.ofString(requestBody))
.build();
try {
// 发送请求并打印结果
HttpResponse<String> response = client.send(
request, HttpResponse.BodyHandlers.ofString());
System.out.println("HTTP Status: " + response.statusCode());
System.out.println("Response Body:\n" + response.body());
} catch (Exception e) {
e.printStackTrace();
}
}
} 模型返回的content：
它们相加等于18.91。
设置模型回答长度限制
多轮对话场景下，随着对话轮数的增加，每次调用消耗的Token数量也会增加，从而增加了使用成本。
这种情况下，可在请求时设置max_tokens字段明确限制模型生成的最大token数量，来限制模型回答长度。各模型的max_tokens取值可参考模型详情页的最大输出长度。
下面是设置模型回答长度限制的示例代码，可通过model参数替换模型，model参数详情请参见文本生成。
import requests
import json
if __name__ == '__main__':
url = # API地址
api_key = "MAAS_API_KEY" # 把MAAS_API_KEY替换成已获取的API Key
# Send request.
headers = {
'Content-Type': 'application/json',
'Authorization': f'Bearer {api_key}'
}
data = {
"model": "glm-5.2", # model参数
"messages": [
{"role": "system", "content": "You are a helpful assistant." },
{"role": "user","content": "你好" }
],
"max_tokens": 1024
}
response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
# Print result.
print(response.status_code)
print(response.text) curl -X POST \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MAAS_API_KEY" \
-d '{
"model": "glm-5.2",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "你好"}
],
"max_tokens": 1024
}' 建议JDK版本为15+。
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.time.Duration;
public class ChatCompletionsExample {
public static void main(String[] args) {
// 接口地址
String apiUrl = "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions";
// 把MAAS_API_KEY替换成已获取的API Key
String apiKey = "MAAS_API_KEY";
// 替换为你要调用的模型名称，例如 "deepseek-v3.2" 等
String modelName = "glm-5.2";
// 构造请求体
String requestBody = String.format(
"""
{
"model": "%s",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "你好"}
],
"max_tokens": 1024
}""", modelName);
// 创建 HttpClient
HttpClient client = HttpClient.newBuilder()
.connectTimeout(Duration.ofSeconds(10))
.build();
// 创建请求
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(apiUrl))
.header("Content-Type", "application/json")
.header("Authorization", "Bearer " + apiKey)
.POST(HttpRequest.BodyPublishers.ofString(requestBody))
.build();
try {
// 发送请求并打印结果
HttpResponse<String> response = client.send(
request, HttpResponse.BodyHandlers.ofString());
System.out.println("HTTP Status: " + response.statusCode());
System.out.println("Response Body:\n" + response.body());
} catch (Exception e) {
e.printStackTrace();
}
}
} 错误码
模型调用过程中，如有报错，请参考错误码排查并处理。
