大模型服务平台 TokenHub Kimi 调用指南

注意：这篇以 TokenHub 平台为例，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 Kimi 模型（具体以 模型列表 为准）：

二、Kimi 各模型调用差异

Kimi 系列模型整体兼容 OpenAI Chat Completions 协议，但不同模型的参数约束不同。接入时请按具体模型 ID 维护参数模板，不要把一套请求参数复用于所有 Kimi 模型。

三、多模态输入限制

Kimi 视觉模型对图片和视频的格式、分辨率及传参方式有以下约束：

注意：说明：

注意：超过建议分辨率不会提升理解效果，只会增加处理耗时。

四、关键调用场景示例

以下示例保留多轮回写、图片输入和视频输入等容易踩坑的场景。示例中的 kimi-k2.6 已在 TokenHub 模型列表中确认为有效调用参数；当前环境没有配置 TokenHub 模型调用 API Key，因此未在本地发起真实推理请求，实际可用性仍以账号权限和控制台模型列表为准。

五、多轮对话回写 reasoning_content

启用思考时，必须把上一轮 API 返回的 reasoning_content 与 content 一并回写到 messages，否则模型在后续轮次中会丢失推理脉络。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "kimi-k2.6", "stream": true, "thinking": {"type": "enabled", "keep": "all"}, "messages": [ {"role": "system", "content": "你是 Kimi。"}, {"role": "user", "content": "第一个问题…"}, { "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": "请基于之前的分析继续推导。"} ] }'from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://tokenhub.tencentmaas.com/v1",)messages = [ {"role": "system", "content": "你是 Kimi。"}, {"role": "user", "content": "第一个问题…"}, { "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": "请基于之前的分析继续推导。"},]response = client.chat.completions.create( model="kimi-k2.6", messages=messages, stream=True, extra_body={"thinking": {"type": "enabled", "keep": "all"}},)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 Kimi。' }, { role: 'user', content: '第一个问题…' }, { 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: '请基于之前的分析继续推导。' },];const stream = await client.chat.completions.create({ model: 'kimi-k2.6', messages, stream: true, thinking: { type: 'enabled', keep: 'all' },});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.io.IOException;import java.util.*;import java.util.concurrent.TimeUnit;public class MultiTurnWithThinking { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(30, TimeUnit.SECONDS) .readTimeout(300, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(600, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "kimi-k2.6"); body.put("stream", true); body.put("thinking", Map.of("type", "enabled", "keep", "all")); body.put("messages", List.of( Map.of("role", "system", "content", "你是 Kimi。"), Map.of("role", "user", "content", "第一个问题…"), 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", "请基于之前的分析继续推导。") )); 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; } 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)); } } } catch (IOException e) { System.err.println("请求异常: " + e.getMessage()); e.printStackTrace(); } }}package mainimport ( "bufio" "bytes" "encoding/json" "fmt" "net/http" "strings")func main() { body, _ := json.Marshal(map[string]interface{}{ "model": "kimi-k2.6", "stream": true, "thinking": map[string]string{"type": "enabled", "keep": "all"}, "messages": []map[string]interface{}{ {"role": "system", "content": "你是 Kimi。"}, {"role": "user", "content": "第一个问题…"}, { "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": "请基于之前的分析继续推导。"}, }, }) 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、1. 图片输入：Base64 编码

适合本地文件 / 内网图片场景：

cURLPythonNode.jsJavaGo# 先把图片读为 base64IMAGE_B64=$(base64 -i image.jpg | tr -d '\\n')# 用临时文件传 body，避免 base64 字符串过大触发 "Argument list too long"cat > /tmp/req.json <<EOF{ "model": "kimi-k2.6", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "请描述这张图片"}, {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,${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="kimi-k2.6", 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 'node: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: 'kimi-k2.6', 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.io.IOException;import java.nio.file.*;import java.util.*;import java.util.Base64;import java.util.concurrent.TimeUnit;public class ImageBase64Chat { public static void main(String[] args) throws IOException { // 请准备你本地的图片文件，支持 PNG/JPG/JPEG/WebP 格式 byte[] bytes = Files.readAllBytes(Paths.get("image.jpg")); String imageB64 = Base64.getEncoder().encodeToString(bytes); OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(30, TimeUnit.SECONDS) .readTimeout(300, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(600, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "kimi-k2.6"); 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," + imageB64 )) ) ))); 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/base64" "encoding/json" "fmt" "io" "net/http" "os")func main() { img, _ := os.ReadFile("image.jpg") imageB64 := base64.StdEncoding.EncodeToString(img) body, _ := json.Marshal(map[string]interface{}{ "model": "kimi-k2.6", "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," + imageB64, }, }, }, }, }, }) 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、2. 图片输入：公网 URL 直链（仅适用于支持 URL 的模型）

适合已托管在 CDN / 对象存储的图片，可显著减小请求体积。但公网 URL 并非所有 Kimi 模型都支持，例如 K3 限制为不支持公网图片 URL，需改用 Base64 或 ms://<file-id>。

cURLPythonNode.jsJavaGocurl -X POST 'https://tokenhub.tencentmaas.com/v1/chat/completions' \\ -H 'Authorization: Bearer YOUR_API_KEY' \\ -H 'Content-Type: application/json' \\ -d '{ "model": "kimi-k2.6", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "请描述这张图片"}, {"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="kimi-k2.6", messages=[{ "role": "user", "content": [ {"type": "text", "text": "请描述这张图片"}, {"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: 'kimi-k2.6', messages: [{ role: 'user', content: [ { type: 'text', text: '请描述这张图片' }, { 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(30, TimeUnit.SECONDS) .readTimeout(300, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(600, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "kimi-k2.6"); body.put("messages", List.of(Map.of( "role", "user", "content", List.of( Map.of("type", "text", "text", "请描述这张图片"), // 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": "kimi-k2.6", "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": "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))}

注意：使用 URL 直链时，请确保该 URL 公网可访问且无需鉴权；私网 / 内网图片或带签名校验的 URL 仍需先下载并以 Base64 方式上传。

八、3. 视频输入（按模型支持情况使用）

视频输入与图片类似，但不同 Kimi 模型支持范围不同：K3、K2.8 Preview、K2.7 Code、K2.6 可按平台能力使用视频输入。具体传入方式请以对应模型的接口约束为准，不应直接将下方 K2.6 示例替换为其他模型 ID。

cURLPythonNode.jsJavaGo# 先把视频读为 base64VIDEO_B64=$(base64 -i demo.mp4 | tr -d '\\n')# 用临时文件传 body，避免 base64 字符串过大触发 "Argument list too long"cat > /tmp/req.json <<EOF{ "model": "kimi-k2.6", "messages": [{ "role": "user", "content": [ {"type": "text", "text": "请总结视频内容"}, {"type": "video_url", "video_url": {"url": "data:video/mp4;base64,${VIDEO_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("demo.mp4", "rb") as f: video_b64 = base64.b64encode(f.read()).decode()response = client.chat.completions.create( model="kimi-k2.6", messages=[{ "role": "user", "content": [ {"type": "text", "text": "请总结视频内容"}, {"type": "video_url", "video_url": {"url": f"data:video/mp4;base64,{video_b64}"}}, ], }],)print(response.choices[0].message.content)import fs from 'node:fs';import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://tokenhub.tencentmaas.com/v1',});const videoB64 = fs.readFileSync('demo.mp4').toString('base64');const response = await client.chat.completions.create({ model: 'kimi-k2.6', messages: [{ role: 'user', content: [ { type: 'text', text: '请总结视频内容' }, { type: 'video_url', video_url: { url: `data:video/mp4;base64,${videoB64}` } }, ], }],});console.log(response.choices[0].message.content);import okhttp3.*;import com.google.gson.Gson;import java.io.IOException;import java.nio.file.*;import java.util.*;import java.util.Base64;import java.util.concurrent.TimeUnit;public class VideoChat { public static void main(String[] args) throws IOException { // 请准备你本地的视频文件，支持 MP4/MOV/AVI 等格式 byte[] bytes = Files.readAllBytes(Paths.get("demo.mp4")); String videoB64 = Base64.getEncoder().encodeToString(bytes); OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(30, TimeUnit.SECONDS) .readTimeout(300, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) .callTimeout(600, TimeUnit.SECONDS) .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "kimi-k2.6"); body.put("messages", List.of(Map.of( "role", "user", "content", List.of( Map.of("type", "text", "text", "请总结视频内容"), Map.of("type", "video_url", "video_url", Map.of( "url", "data:video/mp4;base64," + videoB64 )) ) ))); 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/base64" "encoding/json" "fmt" "io" "net/http" "os")func main() { video, _ := os.ReadFile("demo.mp4") videoB64 := base64.StdEncoding.EncodeToString(video) body, _ := json.Marshal(map[string]interface{}{ "model": "kimi-k2.6", "messages": []map[string]interface{}{ { "role": "user", "content": []map[string]interface{}{ {"type": "text", "text": "请总结视频内容"}, { "type": "video_url", "video_url": map[string]string{ "url": "data:video/mp4;base64," + videoB64, }, }, }, }, }, }) 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))}

注意：说明：

注意：单次请求 body 大小受平台限制（通常 100MB 以内），过大的视频请先压缩或截取关键片段后再上传。

九、Kimi 思考模式

Kimi 系列模型的思考参数需按具体模型配置：K3 和 K2.8 Preview 使用 reasoning_effort，K2.7 Code、K2.6 使用 thinking。

十、1. K3 和 K2.8 Preview：reasoning_effort 参数

kimi-k3 和 kimi-k2.8-preview 始终开启思考模式，通过顶层 reasoning_effort 配置思考力度，支持 "low"、"high"、"max" 三档，默认 "max"。下方以 K3 为例；K2.8 Preview 的输出 token 参数使用 max_tokens。

{ "model": "kimi-k3", "reasoning_effort": "max", "messages": [ {"role": "user", "content": "证明根号 2 是无理数。"} ]}

注意：调用 kimi-k3 和 kimi-k2.8-preview 时不要套用 K2.7 Code、K2.6 的 thinking 配置；多轮对话和工具调用时，需要将 API 返回的完整 assistant message 原样加入下一轮请求，不要只保留 content。

十一、2. K2.7 Code、K2.6：thinking 参数

K2.6 / K2.7 Code 的 thinking 字段位于请求体顶层，结构如下：

"thinking": { "type": "enabled", "keep": "all"}

注意：thinking 不是 OpenAI 标准字段，本节用法适用于 K2.7 Code、K2.6，不直接适用于 K2.8 Preview。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。

十二、3. 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 …" } }]}

十三、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。

十四、4. 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，非流式容易触发服务超时。

·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": "kimi-k2.6", "max_tokens": 32768, "stream": true, "thinking": {"type": "enabled"}, "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="kimi-k2.6", messages=[{"role": "user", "content": "请用一句话解释傅里叶变换。"}], max_tokens=32768, stream=True, extra_body={"thinking": {"type": "enabled"}},)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',});// Node.js SDK 暂未原生支持 thinking / extra_body，直接展开到顶层即可// 注：若使用 TypeScript，最后一个对象后面加 `as any` 绕过类型检查const stream = await client.chat.completions.create({ model: 'kimi-k2.6', messages: [{ role: 'user', content: '请用一句话解释傅里叶变换。' }], max_tokens: 32768, stream: true, thinking: { type: 'enabled' },});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.*;import java.util.concurrent.TimeUnit;public class ThinkingStream { public static void main(String[] args) { OkHttpClient client = new OkHttpClient.Builder() .connectTimeout(30, TimeUnit.SECONDS) .readTimeout(300, TimeUnit.SECONDS) .writeTimeout(60, TimeUnit.SECONDS) // SSE 流式不设 callTimeout，避免整条流被整体超时截断 .build(); Map<String, Object> body = new HashMap<>(); body.put("model", "kimi-k2.6"); body.put("max_tokens", 32768); body.put("stream", true); body.put("thinking", Map.of("type", "enabled")); 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(client).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")) { System.out.print(delta.get("reasoning_content").getAsString()); } if (delta.has("content") && !delta.get("content").isJsonNull()) { System.out.print(delta.get("content").getAsString()); } } @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": "kimi-k2.6", "max_tokens": 32768, "stream": true, "thinking": map[string]string{"type": "enabled"}, "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) } }}

十五、5. Preserved Thinking（多轮保留思考）

本节沿用 K2.7 Code、K2.6 的参数说明，不直接适用于 K2.8 Preview。thinking.keep 控制历史轮次的 reasoning_content 是否参与下一轮推理：

注意：keep 只影响历史思考是否传给模型，不影响当前轮次是否产生思考；推荐在需要连续推理的场景下与 type: "enabled" 搭配使用。