大模型服务平台 TokenHub Qwen 调用指南

注意：这篇以 TokenHub 网关为例，所有调用均通过 https://tokenhub.tencentmaas.com/v1 接入，使用 TokenHub 自有 API Key 完成鉴权。

一、支持的模型

TokenHub 当前支持以下 Qwen 模型（具体以 模型列表 为准）：

注意：说明：

注意：Qwen3.5 系列同时是对话模型和思考模型，无需在普通模型与思考模型之间切换 model ID，通过 enable_thinking 参数即可控制是否启用思考能力。下文示例以 qwen3.5-plus 为例，将 model 参数替换为 qwen3.5-flash 即可切换为轻量版本。

二、与其他模型的关键差异（速查）

下面分别说明每一项的具体用法。

三、通用调用示例

以下是 Qwen3.5-Plus 的常用调用场景，均使用 OpenAI 兼容协议。所有示例与 语言模型调用概览 中的示例代码保持一致写法，调用方式直接复用。Qwen 特有能力（思考模式开关、Prompt 级开关、preserve_thinking 等）见下文 Qwen 思考模式 章节。

四、基础对话

请将 YOUR_API_KEY 替换为你创建的 API Key。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [ {"role": "user", "content": "你好，请介绍一下你自己"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)response = client.chat.completions.create( model="qwen3.5-plus", messages=[ {"role": "user", "content": "你好，请介绍一下你自己"}, ],)print(response.choices[0].message.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [ { role: 'user', content: '你好，请介绍一下你自己' }, ],});console.log(response.choices[0].message.content);// 基于 OpenAI 兼容协议，使用 OkHttp 直接调用 HTTP 接口import okhttp3.*;import com.google.gson.Gson;import java.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class BasicChat { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(180, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of( Map.of("role", "user", "content", "你好，请介绍一下你自己") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = client.newCall(request).execute()) { if (!response.isSuccessful()) { System.err.println("请求失败, HTTP " + response.code() + " : " + (response.body() != null ? response.body().string() : "")); return; } System.out.println(response.body() != null ? response.body().string() : ""); } catch (IOException e) { System.err.println("请求异常: " + e.getMessage()); e.printStackTrace(); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]string{ {"role": "user", "content": "你好，请介绍一下你自己"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

五、流式输出

启用 stream: true 即可流式获取响应，便于打字机效果展示，并能避免长响应触发网关超时。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "stream": true, "messages": [ {"role": "user", "content": "请用一句话介绍一下你自己"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)stream = client.chat.completions.create( model="qwen3.5-plus", messages=[{"role": "user", "content": "请用一句话介绍一下你自己"}], stream=True,)for chunk in stream: if chunk.choices and chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const stream = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: '请用一句话介绍一下你自己' }], stream: true,});for await (const chunk of stream) { const content = chunk.choices?.[0]?.delta?.content; if (content) process.stdout.write(content);}import okhttp3.*;import okhttp3.sse.*;import com.google.gson.Gson;import java.util.*;import java.util.concurrent.TimeUnit;public class StreamChat { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("stream", true); body.put("messages", List.of( Map.of("role", "user", "content", "请用一句话介绍一下你自己") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); EventSources.createFactory(client).newEventSource(request, new EventSourceListener() { @Override public void onEvent(EventSource es, String id, String type, String data) { System.out.println(data); } @Override public void onFailure(EventSource es, Throwable t, Response response) { System.err.println("流式请求失败: " + (t != null ? t.getMessage() : "") + (response != null ? " HTTP " + response.code() : "")); } }); }}package mainimport ( "bufio" "bytes" "encoding/json" "fmt" "net/http" "strings")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "stream": true, "messages": []map[string]string{ {"role": "user", "content": "请用一句话介绍一下你自己"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() scanner := bufio.NewScanner(resp.Body) for scanner.Scan() { line := scanner.Text() if strings.HasPrefix(line, "data: ") { fmt.Println(strings.TrimPrefix(line, "data: ")) } }}

六、System Prompt

通过 system 角色的消息可以为模型设定全局指令、人设、回复风格等。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [ {"role": "system", "content": "你是通义千问，一名严谨的物理学助教，回答需配合简单类比。"}, {"role": "user", "content": "请解释什么是量子纠缠"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)response = client.chat.completions.create( model="qwen3.5-plus", messages=[ {"role": "system", "content": "你是通义千问，一名严谨的物理学助教，回答需配合简单类比。"}, {"role": "user", "content": "请解释什么是量子纠缠"}, ],)print(response.choices[0].message.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [ { role: 'system', content: '你是通义千问，一名严谨的物理学助教，回答需配合简单类比。' }, { role: 'user', content: '请解释什么是量子纠缠' }, ],});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class SystemPromptChat { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(180, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of( Map.of("role", "system", "content", "你是通义千问，一名严谨的物理学助教，回答需配合简单类比。"), Map.of("role", "user", "content", "请解释什么是量子纠缠") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = client.newCall(request).execute()) { if (!response.isSuccessful()) { System.err.println("请求失败, HTTP " + response.code() + " : " + (response.body() != null ? response.body().string() : "")); return; } System.out.println(response.body() != null ? response.body().string() : ""); } catch (IOException e) { System.err.println("请求异常: " + e.getMessage()); e.printStackTrace(); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]string{ {"role": "system", "content": "你是通义千问，一名严谨的物理学助教，回答需配合简单类比。"}, {"role": "user", "content": "请解释什么是量子纠缠"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

七、多轮对话（基础版）

Qwen API 与其他主流模型一样是无状态的，需要在每次请求中传入完整的 messages 历史。下例不开启思考，所以只回写 content 即可；如果启用了思考，建议同时回写 reasoning_content 并开启 preserve_thinking，详见下文 Qwen 思考模式 → 多轮对话保留思考小节。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "推荐一本科普读物"}, {"role": "assistant", "content": "推荐《时间简史》。"}, {"role": "user", "content": "再说一本进阶的"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)messages = [ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "推荐一本科普读物"}, {"role": "assistant", "content": "推荐《时间简史》。"}, {"role": "user", "content": "再说一本进阶的"},]response = client.chat.completions.create( model="qwen3.5-plus", messages=messages,)print(response.choices[0].message.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const messages = [ { role: 'system', content: '你是通义千问。' }, { role: 'user', content: '推荐一本科普读物' }, { role: 'assistant', content: '推荐《时间简史》。' }, { role: 'user', content: '再说一本进阶的' },];const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages,});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class MultiTurnChat { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(180, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of( Map.of("role", "system", "content", "你是通义千问。"), Map.of("role", "user", "content", "推荐一本科普读物"), Map.of("role", "assistant", "content", "推荐《时间简史》。"), Map.of("role", "user", "content", "再说一本进阶的") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = client.newCall(request).execute()) { if (!response.isSuccessful()) { System.err.println("请求失败, HTTP " + response.code() + " : " + (response.body() != null ? response.body().string() : "")); return; } System.out.println(response.body() != null ? response.body().string() : ""); } catch (IOException e) { System.err.println("请求异常: " + e.getMessage()); e.printStackTrace(); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]string{ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "推荐一本科普读物"}, {"role": "assistant", "content": "推荐《时间简史》。"}, {"role": "user", "content": "再说一本进阶的"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

八、Function Calling（工具调用）

Qwen 支持标准的 OpenAI Function Calling 协议。下例演示如何注册一个查天气的工具，并在模型决定调用工具后把工具结果回填给模型。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [ {"role": "user", "content": "今天北京天气怎么样？"} ], "tools": [{ "type": "function", "function": { "name": "get_weather", "description": "查询指定城市的天气", "parameters": { "type": "object", "properties": { "city": {"type": "string", "description": "城市名称"} }, "required": ["city"] } } }], "tool_choice": "auto" }'import jsonfrom openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)tools = [{ "type": "function", "function": { "name": "get_weather", "description": "查询指定城市的天气", "parameters": { "type": "object", "properties": {"city": {"type": "string", "description": "城市名称"}}, "required": ["city"], }, },}]messages = [{"role": "user", "content": "今天北京天气怎么样？"}]# 第 1 轮：模型决定是否调用工具resp = client.chat.completions.create( model="qwen3.5-plus", messages=messages, tools=tools, tool_choice="auto",)msg = resp.choices[0].messagemessages.append(msg.model_dump(exclude_none=True))if msg.tool_calls: for call in msg.tool_calls: args = json.loads(call.function.arguments) # 这里替换为真实业务逻辑 result = {"city": args["city"], "temperature": "22°C", "weather": "晴"} messages.append({ "role": "tool", "tool_call_id": call.id, "content": json.dumps(result, ensure_ascii=False), }) # 第 2 轮：把工具结果送回模型，得到最终回复 final = client.chat.completions.create( model="qwen3.5-plus", messages=messages, tools=tools, ) print(final.choices[0].message.content)else: print(msg.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const tools = [{ type: 'function', function: { name: 'get_weather', description: '查询指定城市的天气', parameters: { type: 'object', properties: { city: { type: 'string', description: '城市名称' } }, required: ['city'], }, },}];const messages = [{ role: 'user', content: '今天北京天气怎么样？' }];const resp = await client.chat.completions.create({ model: 'qwen3.5-plus', messages, tools, tool_choice: 'auto',});const msg = resp.choices[0].message;messages.push(msg);if (msg.tool_calls) { for (const call of msg.tool_calls) { const args = JSON.parse(call.function.arguments); const result = { city: args.city, temperature: '22°C', weather: '晴' }; messages.push({ role: 'tool', tool_call_id: call.id, content: JSON.stringify(result), }); } const final = await client.chat.completions.create({ model: 'qwen3.5-plus', messages, tools, }); console.log(final.choices[0].message.content);} else { console.log(msg.content);}import okhttp3.*;import com.google.gson.*;import java.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class FunctionCallingDemo { static final String URL = "https://tokenhub.tencentmaas.com/v1/chat/completions"; static final String API_KEY = "YOUR_API_KEY"; static final OkHttpClient HTTP = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(180, TimeUnit.SECONDS) .build(); static final Gson GSON = new Gson(); static String chat(List<Map<String, Object>> messages, List<Map<String, Object>> tools) throws IOException { Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", messages); body.put("tools", tools); body.put("tool_choice", "auto"); Request req = new Request.Builder() .url(URL) .header("Authorization", "Bearer " + API_KEY) .header("Content-Type", "application/json") .post(RequestBody.create(GSON.toJson(body), MediaType.parse("application/json"))) .build(); try (Response resp = HTTP.newCall(req).execute()) { if (!resp.isSuccessful()) { throw new IOException("请求失败, HTTP " + resp.code() + " : " + (resp.body() != null ? resp.body().string() : "")); } return resp.body() != null ? resp.body().string() : ""; } } public static void main(String[] args) throws Exception { List<Map<String, Object>> tools = List.of(Map.of( "type", "function", "function", Map.of( "name", "get_weather", "description", "查询指定城市的天气", "parameters", Map.of( "type", "object", "properties", Map.of("city", Map.of("type", "string", "description", "城市名称")), "required", List.of("city") ) ) )); List<Map<String, Object>> messages = new ArrayList<>(); messages.add(Map.of("role", "user", "content", "今天北京天气怎么样？")); String r1 = chat(messages, tools); JsonObject msg = JsonParser.parseString(r1).getAsJsonObject() .getAsJsonArray("choices").get(0).getAsJsonObject() .getAsJsonObject("message"); messages.add(GSON.fromJson(msg, Map.class)); if (msg.has("tool_calls")) { for (JsonElement el : msg.getAsJsonArray("tool_calls")) { JsonObject call = el.getAsJsonObject(); JsonObject argsObj = JsonParser.parseString( call.getAsJsonObject("function").get("arguments").getAsString() ).getAsJsonObject(); Map<String, String> result = Map.of( "city", argsObj.get("city").getAsString(), "temperature", "22°C", "weather", "晴" ); messages.add(Map.of( "role", "tool", "tool_call_id", call.get("id").getAsString(), "content", GSON.toJson(result) )); } System.out.println(chat(messages, tools)); } else { System.out.println(msg.get("content").getAsString()); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")const ( URL = "https://tokenhub.tencentmaas.com/v1/chat/completions" APIKEY = "YOUR_API_KEY")func chat(messages []map[string]interface{}, tools []map[string]interface{}) (map[string]interface{}, error) { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": messages, "tools": tools, "tool_choice": "auto", }) req, _ := http.NewRequest("POST", URL, bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer "+APIKEY) req.Header.Set("Content-Type", "application/json") resp, err := http.DefaultClient.Do(req) if err != nil { return nil, err } defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) var out map[string]interface{} json.Unmarshal(data, &out) return out, nil}func main() { tools := []map[string]interface{}{{ "type": "function", "function": map[string]interface{}{ "name": "get_weather", "description": "查询指定城市的天气", "parameters": map[string]interface{}{ "type": "object", "properties": map[string]interface{}{ "city": map[string]string{"type": "string", "description": "城市名称"}, }, "required": []string{"city"}, }, }, }} messages := []map[string]interface{}{ {"role": "user", "content": "今天北京天气怎么样？"}, } // 第 1 轮：模型决定是否调用工具 r1, _ := chat(messages, tools) msg := r1["choices"].([]interface{})[0].(map[string]interface{})["message"].(map[string]interface{}) messages = append(messages, msg) if calls, ok := msg["tool_calls"].([]interface{}); ok { for _, c := range calls { call := c.(map[string]interface{}) argsStr := call["function"].(map[string]interface{})["arguments"].(string) var args map[string]string json.Unmarshal([]byte(argsStr), &args) result, _ := json.Marshal(map[string]string{ "city": args["city"], "temperature": "22°C", "weather": "晴", }) messages = append(messages, map[string]interface{}{ "role": "tool", "tool_call_id": call["id"], "content": string(result), }) } r2, _ := chat(messages, tools) fmt.Printf("%+v\\n", r2) } else { fmt.Println(msg["content"]) }}

九、多模态调用

Qwen3.5-Plus 是多模态模型，除文本外还支持图片与视频输入，复用 OpenAI 兼容的 image_url / video_url 结构即可。

十、1. 图片输入：URL 形式

适合公网可直接访问的图片：

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "这张图里是什么？请用一句话描述。"}, {"type": "image_url", "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}} ] }] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)response = client.chat.completions.create( model="qwen3.5-plus", messages=[{ "role": "user", "content": [ {"type": "text", "text": "这张图里是什么？请用一句话描述。"}, {"type": "image_url", "image_url": {"url": "https://www.gstatic.com/webp/gallery/1.jpg"}}, ], }],)print(response.choices[0].message.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: [ { type: 'text', text: '这张图里是什么？请用一句话描述。' }, { type: 'image_url', image_url: { url: 'https://www.gstatic.com/webp/gallery/1.jpg' } }, ], }],});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class ImageUrlChat { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(15, TimeUnit.SECONDS) .readTimeout(120, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(180, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of(Map.of( "role", "user", "content", List.of( Map.of("type", "text", "text", "这张图里是什么？请用一句话描述。"), // 请替换为你自己的可公网访问图片 URL Map.of("type", "image_url", "image_url", Map.of("url", "https://example.com/path/to/your/image.jpg")) ) ))); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = client.newCall(request).execute()) { if (!response.isSuccessful()) { System.err.println("请求失败, HTTP " + response.code() + " : " + (response.body() != null ? response.body().string() : "")); return; } System.out.println(response.body() != null ? response.body().string() : ""); } catch (IOException e) { System.err.println("请求异常: " + e.getMessage()); e.printStackTrace(); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]interface{}{{ "role": "user", "content": []map[string]interface{}{ {"type": "text", "text": "这张图里是什么？请用一句话描述。"}, {"type": "image_url", "image_url": map[string]string{"url": "https://www.gstatic.com/webp/gallery/1.jpg"}}, }, }}, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

十一、2. 图片输入：Base64 编码

适合本地文件 / 内网图片场景：

注意：说明：

注意：以下示例从当前目录读取 image.jpg，运行前请准备一张测试图片并命名为 image.jpg 放到当前目录。

cURLPythonNode.jsJavaGo# 先把图片读为 base64IMAGE_B64=$(base64 -i image.jpg | tr -d '\\n')# 用临时文件传 body，避免 base64 字符串过大触发 "Argument list too long"cat > /tmp/req.json <<EOF{ "model": "qwen3.5-plus", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "请描述这张图片"}, {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,${IMAGE_B64}"}} ] }]}EOFcurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d @/tmp/req.jsonimport base64from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)with open("image.jpg", "rb") as f: image_b64 = base64.b64encode(f.read()).decode()response = client.chat.completions.create( model="qwen3.5-plus", messages=[{ "role": "user", "content": [ {"type": "text", "text": "请描述这张图片"}, {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_b64}"}}, ], }],)print(response.choices[0].message.content)import fs from 'fs';import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const imageB64 = fs.readFileSync('image.jpg').toString('base64');const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: [ { type: 'text', text: '请描述这张图片' }, { type: 'image_url', image_url: { url: `data:image/jpeg;base64,${imageB64}` } }, ], }],});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.nio.file.*;import java.util.*;public class ImageBase64Chat { public static void main(String[] args) throws Exception { byte[] bytes = Files.readAllBytes(Path.of("image.jpg")); String b64 = Base64.getEncoder().encodeToString(bytes); Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of(Map.of( "role", "user", "content", List.of( Map.of("type", "text", "text", "请描述这张图片"), Map.of("type", "image_url", "image_url", Map.of("url", "data:image/jpeg;base64," + b64)) ) ))); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = new OkHttpClient().newCall(request).execute()) { System.out.println(response.body().string()); } }}package mainimport ( "bytes" "encoding/base64" "encoding/json" "fmt" "io" "net/http" "os")func main() { raw, _ := os.ReadFile("image.jpg") b64 := base64.StdEncoding.EncodeToString(raw) body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]interface{}{{ "role": "user", "content": []map[string]interface{}{ {"type": "text", "text": "请描述这张图片"}, {"type": "image_url", "image_url": map[string]string{"url": "data:image/jpeg;base64," + b64}}, }, }}, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

十二、3. 视频输入：URL 形式

视频输入与图片类似，将 image_url 替换为 video_url 即可：

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "请简述这段视频的内容"}, {"type": "video_url", "video_url": {"url": "https://www.w3schools.com/html/mov_bbb.mp4"}} ] }] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)response = client.chat.completions.create( model="qwen3.5-plus", messages=[{ "role": "user", "content": [ {"type": "text", "text": "请简述这段视频的内容"}, {"type": "video_url", "video_url": {"url": "https://www.w3schools.com/html/mov_bbb.mp4"}}, ], }],)print(response.choices[0].message.content)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const response = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: [ { type: 'text', text: '请简述这段视频的内容' }, { type: 'video_url', video_url: { url: 'https://www.w3schools.com/html/mov_bbb.mp4' } }, ], }],});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.util.*;public class VideoUrlChat { public static void main(String[] args) throws Exception { Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("messages", List.of(Map.of( "role", "user", "content", List.of( Map.of("type", "text", "text", "请简述这段视频的内容"), Map.of("type", "video_url", "video_url", Map.of("url", "https://www.w3schools.com/html/mov_bbb.mp4")) ) ))); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = new OkHttpClient().newCall(request).execute()) { System.out.println(response.body().string()); } }}package mainimport ( "bytes" "encoding/json" "fmt" "io" "net/http")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "messages": []map[string]interface{}{{ "role": "user", "content": []map[string]interface{}{ {"type": "text", "text": "请简述这段视频的内容"}, {"type": "video_url", "video_url": map[string]string{"url": "https://www.w3schools.com/html/mov_bbb.mp4"}}, }, }}, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() data, _ := io.ReadAll(resp.Body) fmt.Println(string(data))}

十三、Qwen 思考模式

Qwen3.5-Plus 同时是对话模型和思考模型，默认开启思考，通过 enable_thinking 字段控制思考能力开关，并提供 Prompt 级开关、preserve_thinking 等独有能力。

十四、1. enable_thinking 参数

enable_thinking 是请求体顶层的布尔字段：

注意：enable_thinking 不是 OpenAI 标准字段，使用 SDK 时需通过 extra_body（Python）或直接展开到顶层（Node.js）透传；HTTP 直接调用时放在请求体顶层即可。

十五、2. reasoning_content 字段

启用思考后，响应消息中会新增一个与 content 同级的 reasoning_content 字段，承载模型的推理过程：

{ "choices": [{ "message": { "role": "assistant", "reasoning_content": "首先我们需要分析…", "content": "最终答案是 …" } }]}

十六、OpenAI SDK 访问限制（重要）

OpenAI SDK 的 ChatCompletionMessage / ChoiceDelta 类型不直接声明 reasoning_content 属性，因此不能用 obj.reasoning_content 直接访问，必须用以下方式：

# ❌ 错误content = message.reasoning_content# ✅ 正确if hasattr(message, "reasoning_content"): content = getattr(message, "reasoning_content")

如果你是通过 HTTP 直接调用、或使用 requests / httpx 等通用框架解析 JSON，则无此限制，可直接读取同级字段。

十七、3. 流式思考输出

启用思考时强烈建议使用流式调用（stream: true）：

·避免超时：思考内容可能较长，整体响应时间较久，非流式容易触发网关超时。

·顺序明确：流式模式下 reasoning_content 一定在 content 之前完整输出，便于 UI 区分思考中和正在回答两种状态。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "messages": [ {"role": "user", "content": "请用一句话解释傅里叶变换。"} ] }'# 响应为 SSE 流：每个 data: 行包含一个 chunk，# delta.reasoning_content 一定先于 delta.content 出现from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)stream = client.chat.completions.create( model="qwen3.5-plus", messages=[{"role": "user", "content": "请用一句话解释傅里叶变换。"}], stream=True, extra_body={ "enable_thinking": True, },)thinking = Falsefor chunk in stream: if not chunk.choices: continue delta = chunk.choices[0].delta # 思考阶段 if hasattr(delta, "reasoning_content") and getattr(delta, "reasoning_content"): if not thinking: print("=== 开始思考 ===") thinking = True print(getattr(delta, "reasoning_content"), end="", flush=True) # 回答阶段 if delta.content: if thinking: print("\\n=== 思考结束 ===") thinking = False print(delta.content, end="", flush=True)import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const stream = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: '请用一句话解释傅里叶变换。' }], stream: true, enable_thinking: true,});let thinking = false;for await (const chunk of stream) { const delta = chunk.choices?.[0]?.delta; if (!delta) continue; if (delta.reasoning_content) { if (!thinking) { console.log('=== 开始思考 ==='); thinking = true; } process.stdout.write(delta.reasoning_content); } if (delta.content) { if (thinking) { console.log('\\n=== 思考结束 ==='); thinking = false; } process.stdout.write(delta.content); }}import okhttp3.*;import okhttp3.sse.*;import com.google.gson.*;import java.util.*;public class ThinkingStream { public static void main(String[] args) { Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("stream", true); body.put("enable_thinking", true); body.put("messages", List.of( Map.of("role", "user", "content", "请用一句话解释傅里叶变换。") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); EventSources.createFactory(new OkHttpClient()).newEventSource(request, new EventSourceListener() { @Override public void onEvent(EventSource es, String id, String type, String data) { if ("[DONE]".equals(data)) return; JsonObject delta = JsonParser.parseString(data).getAsJsonObject() .getAsJsonArray("choices").get(0).getAsJsonObject() .getAsJsonObject("delta"); if (delta.has("reasoning_content") && !delta.get("reasoning_content").isJsonNull()) { System.out.print(delta.get("reasoning_content").getAsString()); } if (delta.has("content") && !delta.get("content").isJsonNull()) { System.out.print(delta.get("content").getAsString()); } } }); }}package mainimport ( "bufio" "bytes" "encoding/json" "fmt" "net/http" "strings")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "messages": []map[string]string{ {"role": "user", "content": "请用一句话解释傅里叶变换。"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() scanner := bufio.NewScanner(resp.Body) thinking := false for scanner.Scan() { line := scanner.Text() if !strings.HasPrefix(line, "data: ") { continue } data := strings.TrimPrefix(line, "data: ") if data == "[DONE]" { break } var chunk map[string]interface{} if err := json.Unmarshal([]byte(data), &chunk); err != nil { continue } choices, _ := chunk["choices"].([]interface{}) if len(choices) == 0 { continue } delta, _ := choices[0].(map[string]interface{})["delta"].(map[string]interface{}) if rc, ok := delta["reasoning_content"].(string); ok && rc != "" { if !thinking { fmt.Println("=== 开始思考 ===") thinking = true } fmt.Print(rc) } if c, ok := delta["content"].(string); ok && c != "" { if thinking { fmt.Println("\\n=== 思考结束 ===") thinking = false } fmt.Print(c) } }}

十八、4. Prompt 级思考开关（Qwen 独有）

除了 enable_thinking 字段，Qwen 还支持在用户消息内容中加入 Prompt 级开关，方便在多轮对话中仅对单条消息临时切换思考状态：

注意：说明：

注意：多个标记同时出现时以最后一条为准。该机制需要 enable_thinking: true 配合使用，仅作用于当前轮次，不改变全局参数。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "messages": [ {"role": "user", "content": "你好 /no_think"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)# Prompt 级开关：在 user 消息文本里直接加入 /no_think 或 /thinkstream = client.chat.completions.create( model="qwen3.5-plus", messages=[{"role": "user", "content": "你好 /no_think"}], stream=True, extra_body={"enable_thinking": True},)for chunk in stream: delta = chunk.choices[0].delta if delta.content: print(delta.content, end="", flush=True)print()import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});// Prompt 级开关：在 user 消息文本里直接加入 /no_think 或 /thinkconst stream = await client.chat.completions.create({ model: 'qwen3.5-plus', messages: [{ role: 'user', content: '你好 /no_think' }], stream: true, enable_thinking: true,});for await (const chunk of stream) { const delta = chunk.choices?.[0]?.delta; if (delta?.content) process.stdout.write(delta.content);}console.log();import okhttp3.*;import com.google.gson.Gson;import java.util.*;public class PromptThinkSwitch { public static void main(String[] args) throws Exception { Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("stream", true); body.put("enable_thinking", true); body.put("messages", List.of( Map.of("role", "user", "content", "你好 /no_think") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = new OkHttpClient().newCall(request).execute()) { // 流式 SSE：逐行读取 data: 行 try (java.io.BufferedReader r = new java.io.BufferedReader( new java.io.InputStreamReader(response.body().byteStream()))) { String line; while ((line = r.readLine()) != null) { if (line.startsWith("data: ")) System.out.println(line.substring(6)); } } } }}package mainimport ( "bufio" "bytes" "encoding/json" "fmt" "net/http" "strings")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "messages": []map[string]string{ {"role": "user", "content": "你好 /no_think"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() scanner := bufio.NewScanner(resp.Body) for scanner.Scan() { line := scanner.Text() if strings.HasPrefix(line, "data: ") { fmt.Println(strings.TrimPrefix(line, "data: ")) } }}

十九、5. 多轮对话保留思考（preserve_thinking，Qwen 独有）

preserve_thinking 控制历史轮次的 reasoning_content 是否参与下一轮推理：

注意：开启 preserve_thinking: true 后，历史 reasoning_content 会计入输入 Token 数和计费，请按需启用。多轮 Function Calling 场景下建议开启，可显著提升后续轮次的准确性。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "preserve_thinking": true, "messages": [ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "我需要为电商系统选消息队列"}, { "role": "assistant", "reasoning_content": "<上一轮 API 返回的 reasoning_content>", "content": "<上一轮 API 返回的 content>" }, {"role": "user", "content": "你为何排除了 Kafka？"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)messages = [ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "我需要为电商系统选消息队列"}, { "role": "assistant", "reasoning_content": "<上一轮 API 返回的 reasoning_content>", "content": "<上一轮 API 返回的 content>", }, {"role": "user", "content": "你为何排除了 Kafka？"},]response = client.chat.completions.create( model="qwen3.5-plus", messages=messages, stream=True, extra_body={ "enable_thinking": True, "preserve_thinking": True, },)for chunk in response: delta = chunk.choices[0].delta if getattr(delta, "reasoning_content", None): print(delta.reasoning_content, end="", flush=True) if delta.content: print(delta.content, end="", flush=True)print()import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const messages = [ { role: 'system', content: '你是通义千问。' }, { role: 'user', content: '我需要为电商系统选消息队列' }, { role: 'assistant', reasoning_content: '<上一轮 API 返回的 reasoning_content>', content: '<上一轮 API 返回的 content>', }, { role: 'user', content: '你为何排除了 Kafka？' },];const stream = await client.chat.completions.create({ model: 'qwen3.5-plus', messages, stream: true, enable_thinking: true, preserve_thinking: true,});for await (const chunk of stream) { const delta = chunk.choices?.[0]?.delta; if (!delta) continue; if (delta.reasoning_content) process.stdout.write(delta.reasoning_content); if (delta.content) process.stdout.write(delta.content);}console.log();import okhttp3.*;import com.google.gson.Gson;import java.util.*;public class MultiTurnPreserveThinking { public static void main(String[] args) { Map<String, Object> body = new HashMap<>(); body.put("model", "qwen3.5-plus"); body.put("stream", true); body.put("enable_thinking", true); body.put("preserve_thinking", true); body.put("messages", List.of( Map.of("role", "system", "content", "你是通义千问。"), Map.of("role", "user", "content", "我需要为电商系统选消息队列"), Map.of( "role", "assistant", "reasoning_content", "<上一轮 API 返回的 reasoning_content>", "content", "<上一轮 API 返回的 content>" ), Map.of("role", "user", "content", "你为何排除了 Kafka？") )); Request request = new Request.Builder() .url("https://tokenhub.tencentmaas.com/v1/chat/completions") .header("Authorization", "Bearer YOUR_API_KEY") .post(RequestBody.create(new Gson().toJson(body), MediaType.parse("application/json"))) .build(); try (Response response = new OkHttpClient().newCall(request).execute(); java.io.BufferedReader r = new java.io.BufferedReader( new java.io.InputStreamReader(response.body().byteStream()))) { String line; while ((line = r.readLine()) != null) { if (line.startsWith("data: ")) System.out.println(line.substring(6)); } } }}package mainimport ( "bufio" "bytes" "encoding/json" "fmt" "net/http" "strings")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "qwen3.5-plus", "stream": true, "enable_thinking": true, "preserve_thinking": true, "messages": []map[string]interface{}{ {"role": "system", "content": "你是通义千问。"}, {"role": "user", "content": "我需要为电商系统选消息队列"}, { "role": "assistant", "reasoning_content": "<上一轮 API 返回的 reasoning_content>", "content": "<上一轮 API 返回的 content>", }, {"role": "user", "content": "你为何排除了 Kafka？"}, }, }) req, _ := http.NewRequest("POST", "https://tokenhub.tencentmaas.com/v1/chat/completions", bytes.NewBuffer(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, _ := http.DefaultClient.Do(req) defer resp.Body.Close() scanner := bufio.NewScanner(resp.Body) for scanner.Scan() { line := scanner.Text() if strings.HasPrefix(line, "data: ") { fmt.Println(strings.TrimPrefix(line, "data: ")) } }}

20、推荐参数与最佳实践