# 快速入门 > 全部文档的索引见 [llms.txt](https://ark.volcengine.com/llms.txt)；在任一文档页面地址后追加 `.md` 可获取该页的 Markdown 版本。 数分钟内完成您的首次 API 调用。 **[快速入门(新手版)](/docs/quick-start-beginner)** 为零基础用户设计的快速入门 **[方舟文档 MCP](/docs/tutorials-mcp)** 极简配置，协同 AI 完成大模型开发 **[Agent Plan](/docs/agent-plan-personal-get-started)** 一站式智能体开发方案，快速搭建专属 AI Agent # 1 获取并配置 API Key 1. 获取 API Key：在控制台左下角切换到目标项目，在左侧导航中选择 [**API Key 管理**](https://ark.volcengine.com/region:cn-beijing/apiKey)，创建或获取方舟 API Key。 2. 配置环境变量：在终端中运行下面命令（替换 `your_api_key_here` 为您的方舟 API Key），配置 API Key 到环境变量。 配置持久化环境变量方法参见 [环境变量配置指南](/docs/environment-variable-configuration-guide)。 **选项：macOS** ```Bash export ARK_API_KEY="your_api_key_here" ``` **选项：Linux** ```Bash export ARK_API_KEY="your_api_key_here" ``` **选项：Windows_CMD** ```Bash setx ARK_API_KEY "your_api_key_here" ``` **选项：Windows_PowerShell** ```PowerShell $env:ARK_API_KEY = "your_api_key_here" ``` # 2 开通模型服务 访问 [开通管理页面](https://ark.volcengine.com/region:cn-beijing/openManagement) 开通模型服务。 # 3 安装 SDK 安装方舟官方 SDK 或第三方 SDK。 **选项：Python** > 运行环境中需安装 [Python](https://www.python.org/downloads/) 版本 3.8 或以上。 * 安装方舟官方 SDK： ```Bash python -m pip install --upgrade arkruntime ``` * 安装 OpenAI SDK： ```Bash pip install openai ``` **选项：Go** > 环境中安装 [Go](https://golang.google.cn/doc/install) 版本 1.20 或以上。 运行以下命令安装方舟官方 Go SDK： ```Bash go get github.com/volcengine/ark-runtime-go@latest ``` 在代码中引入： ```Go import "github.com/volcengine/ark-runtime-go/arkruntime" ``` **选项：Java** > 环境中安装 [Java](https://www.java.com/en/download/help/index_installing.html) 版本 1.8 或以上。 在项目的 `pom.xml` 文件中添加以下依赖配置。 ```XML com.volcengine ark-runtime ``` > **说明** > > 请从 [Maven Central](https://central.sonatype.com/artifact/com.volcengine/ark-runtime) 获取最新稳定版本，并将 `` 替换为该版本号。 # 4 发起 API 请求 以下按输入输出类别列举的典型任务，选择任意示例代码体验如何通过 API 调用及体验大模型及方舟平台能力。 ## 文本生成 传入文本类信息给模型，进行问答、分析、改写、摘要、编程、翻译等任务，并返回文本结果。 |输入 |输出预览 | | --- | --- | |Hello |* 思考：Got it, let\'s see. The user said "hello". I need to respond in a friendly and welcoming way. Since the system prompt mentions a professional but friendly tone, I should keep it natural. Maybe something like "Hello! How can I assist you today?" That\'s simple, polite, and open-ended to encourage the user to share what they need help with. | \ | |* 回答：Hello! How can I assist you today? Whether you have a question, need help with something specific, or just want to chat, feel free to let me know. 😊 | **选项：Python** ```Python import os from arkruntime import Ark client = Ark( base_url='https://ark.cn-beijing.volces.com/api/v3', api_key=os.getenv('ARK_API_KEY'), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input="hello" ) for item in response.output: if item.type == "message": for content in item.content: if content.type == "output_text": print(content.text) ``` **选项：Curl** ```Bash # Get API Key: https://ark.volcengine.com/region:cn-beijing/apikey curl https://ark.cn-beijing.volces.com/api/v3/responses \ -H "Authorization: Bearer $ARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "doubao-seed-2-1-pro-260915", "input": "hello" }' ``` * 关闭深度思考：配置 `"thinking":{"type": "disabled"} `。 **选项：Go** ```Go package main import ( "context" "fmt" "os" "github.com/volcengine/ark-runtime-go/arkruntime" "github.com/volcengine/ark-runtime-go/arkruntime/model/responses" ) func main() { client := arkruntime.NewClientWithApiKey( // Get API Key: https://ark.volcengine.com/region:cn-beijing/apikey os.Getenv("ARK_API_KEY"), arkruntime.WithBaseUrl("https://ark.cn-beijing.volces.com/api/v3"), ) ctx := context.Background() resp, err := client.CreateResponses(ctx, &responses.ResponsesRequest{ Model: "doubao-seed-2-1-pro-260915", Input: responses.NewStringResponsesInput("hello"), }) if err != nil { fmt.Printf("response error: %v\n", err) return } fmt.Println(resp) } ``` **选项：Java** ```Java package com.ark.example; import com.volcengine.ark.runtime.service.ArkService; import com.volcengine.ark.runtime.models.responses.*; public class demo { public static void main(String[] args) { String apiKey = System.getenv("ARK_API_KEY"); // The base URL for model invocation ArkService arkService = ArkService.builder().apiKey(apiKey) .baseUrl("https://ark.cn-beijing.volces.com/api/v3") .build(); ResponsesRequest request = ResponsesRequest.builder() .model("doubao-seed-2-1-pro-260915") .input(ResponsesInput.ofString("hello")) .build(); Response resp = arkService.createResponse(request); System.out.println(resp); arkService.shutdownExecutor(); } } ``` **选项：OpenAI SDK** ```Python import os from openai import OpenAI client = OpenAI( base_url='https://ark.cn-beijing.volces.com/api/v3', api_key=os.getenv('ARK_API_KEY'), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input="hello" ) for item in response.output: if item.type == "message": for content in item.content: if content.type == "output_text": print(content.text) ``` * [文本生成](/docs/text-generation)：文本生成使用指南。 * [深度思考](/docs/responses-api-deep-thinking)：深度思考能力使用指南。 * [迁移至 Responses API](/docs/responses-api-migration)：新用户推荐，更简洁的上下文管理能力、强大的工具调用能力。 * [Chat API](/docs/chat-api)：存量业务迭代推荐，广泛使用的 API。 ## 多模态理解 传入图片、视频、PDF 文件给模型，进行分析、内容审核、问答、视觉定位等基于多模态理解相关任务，并返回文本结果。 |输入 |输出预览 | | --- | --- | |![](https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png) |* 思考：表格列出了水星、金星、地球、火星、木星、土星、天王星和海王星，共 8 颗行星。地球位于第 3 个数据行。 | \ | |* 回答：表格中列出了 8 颗行星。地球位于第 3 个数据行；如果把表头算作第 1 行，则地球位于第 4 行。 | \ |> 根据图片，表格中列出了多少颗行星，地球位于哪一行？ | | **选项：Python** ```Python import os from arkruntime import Ark client = Ark( base_url='https://ark.cn-beijing.volces.com/api/v3', api_key=os.getenv('ARK_API_KEY'), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input=[ { "role": "user", "content": [ { "type": "input_image", "image_url": "https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png" }, { "type": "input_text", "text": "根据图片，表格中列出了多少颗行星，地球位于哪一行？" }, ], } ] ) for item in response.output: if item.type == "reasoning": for summary in item.summary: if summary.type == "summary_text": print(f"思考：{summary.text}") elif item.type == "message": for content in item.content: if content.type == "output_text": print(f"回答：{content.text}") ``` **选项：Curl** ```Bash curl https://ark.cn-beijing.volces.com/api/v3/responses \ -H "Authorization: Bearer $ARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "doubao-seed-2-1-pro-260915", "input": [ { "role": "user", "content": [ { "type": "input_image", "image_url": "https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png" }, { "type": "input_text", "text": "根据图片，表格中列出了多少颗行星，地球位于哪一行？" } ] } ] }' ``` **选项：Go** ```Go package main import ( "context" "fmt" "os" "github.com/volcengine/ark-runtime-go/arkruntime" "github.com/volcengine/ark-runtime-go/arkruntime/model/responses" ) func main() { client := arkruntime.NewClientWithApiKey( // Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey os.Getenv("ARK_API_KEY"), arkruntime.WithBaseUrl("https://ark.cn-beijing.volces.com/api/v3"), ) ctx := context.Background() inputMessage := responses.InputItem{ OneOf: responses.NewItemEasyMessageInputItemSum( responses.ItemEasyMessage{ Role: responses.NewOptMessageRole(responses.MessageRoleUser), Content: responses.NewContentItemArrayMessageContent( []responses.ContentItem{ responses.ContentItem{OneOf: responses.NewContentItemImageContentItemSum(responses.ContentItemImage{Type: responses.ContentItemImageTypeInputImage, ImageURL: responses.NewOptString("https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png")})}, responses.ContentItem{OneOf: responses.NewContentItemTextContentItemSum(responses.ContentItemText{Type: responses.ContentItemTextTypeInputText, Text: "根据图片，表格中列出了多少颗行星，地球位于哪一行？"})}, }, ), }, ), } resp, err := client.CreateResponses(ctx, &responses.ResponsesRequest{ Model: "doubao-seed-2-1-pro-260915", Input: responses.NewInputItemArrayResponsesInput([]responses.InputItem{inputMessage}), }) if err != nil { fmt.Printf("response error: %v\n", err) return } fmt.Println(resp) } ``` **选项：Java** ```Java package com.ark.sample; import com.volcengine.ark.runtime.service.ArkService; import com.volcengine.ark.runtime.models.responses.*; public class demo { public static void main(String[] args) { String apiKey = System.getenv("ARK_API_KEY"); ArkService arkService = ArkService.builder().apiKey(apiKey) .baseUrl("https://ark.cn-beijing.volces.com/api/v3") .build(); ResponsesRequest request = ResponsesRequest.builder() .model("doubao-seed-2-1-pro-260915") .input(ResponsesInput.ofList(java.util.Arrays.asList(ItemEasyMessage.builder().role(MessageRole.USER).content( MessageContent.ofList(java.util.Arrays.asList(ContentItemImage.builder() .imageUrl("https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png").build(), ContentItemText.builder().text("根据图片，表格中列出了多少颗行星，地球位于哪一行？").build()))) .build()))) .build(); Response resp = arkService.createResponse(request); System.out.println(resp); arkService.shutdownExecutor(); } } ``` **选项：OpenAI SDK** ```Python import os from openai import OpenAI client = OpenAI( base_url='https://ark.cn-beijing.volces.com/api/v3', api_key=os.getenv('ARK_API_KEY'), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input=[ { "role": "user", "content": [ { "type": "input_image", "image_url": "https://arkdocs.tos-cn-beijing.volces.com/images/advanced-usage/planet_comparison.png" }, { "type": "input_text", "text": "根据图片，表格中列出了多少颗行星，地球位于哪一行？" }, ], } ] ) for item in response.output: if item.type == "reasoning": for summary in item.summary: if summary.type == "summary_text": print(f"思考：{summary.text}") elif item.type == "message": for content in item.content: if content.type == "output_text": print(f"回答：{content.text}") ``` * [多模态理解](/docs/multimodal-understanding)：多模态理解详细使用指南。 * [视觉定位 Grounding](/docs/grounding)：图片中找到对应目标并返回坐标任务。 * [文件输入(Files API)](/docs/file-api)：传入图片、视频、文档接口。 * [GUI Agent 能力](/docs/gui-task-processing)：在计算机/移动设备中完成自动化任务。 ## 图片生成 传入图片、文字给模型，进行以下场景&任务： * 广告、海报、组图等图片生成； * 增改元素、颜色更换等图片编辑； * 油墨、水墨等风格切换。 |提示词 |输出预览 | | --- | --- | |充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有 Vogue 杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。 |![](https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/00fb66006eb84b16965b620b6e1f2d78~tplv-goo7wpa0wc-image.image) | **选项：Python** ```Python import os # Install SDK: python -m pip install --upgrade arkruntime from arkruntime import Ark client = Ark( # The base URL for model invocation base_url="https://ark.cn-beijing.volces.com/api/v3", # Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey api_key=os.getenv('ARK_API_KEY'), ) imagesResponse = client.images.generate( # Replace with Model ID model="doubao-seedream-5-0-260128", prompt="充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有Vogue杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。", size="2K", response_format="url", watermark=True ) print(imagesResponse.data[0].url) ``` **选项：Curl** ```Bash curl https://ark.cn-beijing.volces.com/api/v3/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $ARK_API_KEY" \ -d '{ "model": "doubao-seedream-5-0-260128", "prompt": "充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有Vogue杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。", "size": "2K", "watermark": true }' ``` * 您可按需替换 Model ID。Model ID 查询见 [模型列表](/docs/model-list)。 **选项：Java** ```Java package com.ark.sample; import com.volcengine.ark.runtime.models.images.*; import com.volcengine.ark.runtime.service.ArkService; import okhttp3.ConnectionPool; import okhttp3.Dispatcher; import java.util.concurrent.TimeUnit; public class ImageGenerationsExample { public static void main(String[] args) { // Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey String apiKey = System.getenv("ARK_API_KEY"); ConnectionPool connectionPool = new ConnectionPool(5, 1, TimeUnit.SECONDS); Dispatcher dispatcher = new Dispatcher(); ArkService service = ArkService.builder() .baseUrl("https://ark.cn-beijing.volces.com/api/v3") // The base URL for model invocation .dispatcher(dispatcher) .connectionPool(connectionPool) .apiKey(apiKey) .build(); CreateImageGenerationRequest generateRequest = CreateImageGenerationRequest.builder() .model("doubao-seedream-5-0-260128") // Replace with Model ID .prompt("充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有Vogue杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。") .size("2K") .sequentialImageGeneration(SequentialImageGenerationMode.DISABLED) .responseFormat(ResponseFormat.URL) .stream(false) .watermark(true) .build(); ImageGenerationResponse imagesResponse = service.generateImages(generateRequest); System.out.println(imagesResponse.getData().get(0).getUrl()); service.shutdownExecutor(); } } ``` **选项：Go** ```Go package main import ( "context" "fmt" "os" "github.com/volcengine/ark-runtime-go/arkruntime" model "github.com/volcengine/ark-runtime-go/arkruntime/model/images" ) func main() { client := arkruntime.NewClientWithApiKey( os.Getenv("ARK_API_KEY"), // Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey arkruntime.WithBaseUrl("https://ark.cn-beijing.volces.com/api/v3"), // The base URL for model invocation ) ctx := context.Background() generateReq := &model.CreateImageGenerationRequest{ Model: "doubao-seedream-5-0-260128", // Replace with Model ID Prompt: model.NewOptString("充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有Vogue杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。"), Size: model.NewOptString("2K"), ResponseFormat: model.NewOptResponseFormat(model.ResponseFormatURL), Watermark: model.NewOptBool(true), } imagesResponse, err := client.GenerateImages(ctx, generateReq) if err != nil { fmt.Printf("generate images error: %v\n", err) return } fmt.Printf("%s\n", imagesResponse.Data[0].URL.Or("")) } ``` **选项：OpenAI** ```Python import os from openai import OpenAI client = OpenAI( base_url="https://ark.cn-beijing.volces.com/api/v3", # The base URL for model invocation api_key=os.getenv('ARK_API_KEY'), # Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey ) imagesResponse = client.images.generate( # Replace with Model ID model="doubao-seedream-5-0-260128", prompt="充满活力的特写编辑肖像，模特眼神犀利，头戴雕塑感帽子，色彩拼接丰富，眼部焦点锐利，景深较浅，具有Vogue杂志封面的美学风格，采用中画幅拍摄，工作室灯光效果强烈。", size="2K", response_format="url", extra_body={ "watermark": True, }, ) print(imagesResponse.data[0].url) ``` * [Doubao Seedream 4.0-5.0 教程](/docs/seedream-4-0-5-0)：主流生图模型能力以及如何通过 API 调用。 * [Seedream 4.0-5.0 提示词指南](/docs/seedream-4-0-5-0-prompt-guide)：使用生图模型时，如何编写提示词。 ## 视频生成 通过文本描述、图像素材、视频素材，快速生成高质量、风格多样的视频内容。 |提示词 |输出画面预览 | | --- | --- | |一位身穿绿色亮片礼服的女性站在粉红色背景前，周围飘落着五彩斑斓的彩纸。 |![](https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/aae3d0c636954bdd9e66e7a23e98c480~tplv-goo7wpa0wc-image.image) | **选项：Python** ```Python import os import time # Install SDK: python -m pip install --upgrade arkruntime from arkruntime import Ark client = Ark( base_url="https://ark.cn-beijing.volces.com/api/v3", # The base URL for model invocation api_key=os.environ.get("ARK_API_KEY"), # Get API Key：https://ark.volcengine.com/region:cn-beijing/apikey ) if __name__ == "__main__": print("----- create request -----") create_result = client.content_generation.tasks.create( model="doubao-seedance-2-5-260628", # Replace with Model ID content=[ { # Combination of text prompt and parameters "type": "text", "text": "一位身穿绿色亮片礼服的女性站在粉红色背景前，周围飘落着五彩斑斓的彩纸 --wm true --dur 5" } ], watermark=True, ) print(create_result) # Polling query section print("----- polling task status -----") task_id = create_result.id max_wait = 600 # Maximum wait time in seconds interval = 10 # Initial polling interval start = time.time() while time.time() - start < max_wait: get_result = client.content_generation.tasks.get(task_id=task_id) status = get_result.status if status == "succeeded": print("----- task succeeded -----") print(get_result) break elif status == "failed": print("----- task failed -----") print(f"Error: {get_result.error}") break else: print(f"Current status: {status}, retrying after {interval:.0f}s...") time.sleep(interval) interval = min(interval * 1.5, 30) else: raise TimeoutError(f"Task {task_id} timed out after {max_wait}s. " f"Task may still be running - check status manually.") ``` **选项：Java** ```Java package com.ark.sample; import java.util.ArrayList; import java.util.List; import java.util.concurrent.TimeUnit; import com.volcengine.ark.runtime.models.content_generation.*; import com.volcengine.ark.runtime.service.ArkService; public class ContentGenerationTaskExample { public static void main(String[] args) { String apiKey = System.getenv("ARK_API_KEY"); ArkService service = ArkService.builder() .baseUrl("https://ark.cn-beijing.volces.com/api/v3") // The base URL for model invocation .apiKey(apiKey) .build(); System.out.println("----- create request -----"); List contents = new ArrayList<>(); contents.add(ContentItem.builder() .type(ContentType.TEXT) .text("一位身穿绿色亮片礼服的女性站在粉红色背景前，周围飘落着五彩斑斓的彩纸 --wm true --dur 5") .build()); // Create a video generation task CreateContentGenerationTaskRequest createRequest = CreateContentGenerationTaskRequest.builder() .model("doubao-seedance-2-5-260628") // Replace with Model ID .content(contents) .watermark(true) .build(); CreateContentGenerationTaskResponse createResult = service.createContentGenerationTask(createRequest); System.out.println(createResult); // Get the details of the task String taskId = createResult.getId(); String getRequest = taskId; System.out.println("----- polling task status -----"); while (true) { try { ContentGenerationTask getResponse = service.getContentGenerationTask(getRequest); String status = getResponse.getStatus().toString(); if ("succeeded".equalsIgnoreCase(status)) { System.out.println("----- task succeeded -----"); System.out.println(getResponse); service.shutdownExecutor(); break; } else if ("failed".equalsIgnoreCase(status)) { System.out.println("----- task failed -----"); System.out.println("Error: " + getResponse.getStatus()); service.shutdownExecutor(); break; } else { System.out.printf("Current status: %s, Retrying in 3 seconds...\n", status); TimeUnit.SECONDS.sleep(3); } } catch (InterruptedException ie) { Thread.currentThread().interrupt(); System.err.println("Polling interrupted"); service.shutdownExecutor(); break; } } } } ``` **选项：Go** ```Go package main import ( "context" "fmt" "os" "time" "github.com/volcengine/ark-runtime-go/arkruntime" model "github.com/volcengine/ark-runtime-go/arkruntime/model/contentgeneration" ) func main() { client := arkruntime.NewClientWithApiKey( os.Getenv("ARK_API_KEY"), // Get API Key: https://ark.volcengine.com/region:cn-beijing/apikey arkruntime.WithBaseUrl("https://ark.cn-beijing.volces.com/api/v3"), // The base URL for model invocation ) ctx := context.Background() // Replace with Model ID modelEp := "doubao-seedance-2-5-260628" fmt.Println("----- create request -----") createReq := &model.CreateContentGenerationTaskRequest{ Model: modelEp, Content: []model.ContentItem{ { Type: model.ContentTypeText, Text: model.NewOptString("一位身穿绿色亮片礼服的女性站在粉红色背景前，周围飘落着五彩斑斓的彩纸 --wm true --dur 5"), }, }, Watermark: model.NewOptBool(true), } createResp, err := client.CreateContentGenerationTask(ctx, createReq) if err != nil { fmt.Printf("create content generation error: %v", err) return } taskID := createResp.ID fmt.Printf("Task Created with ID: %s", taskID) // Polling query section fmt.Println("----- polling task status -----") for { getReq := taskID getResp, err := client.GetContentGenerationTask(ctx, getReq) if err != nil { fmt.Printf("get content generation task error: %v", err) return } status := getResp.Status if status == "succeeded" { fmt.Println("----- task succeeded -----") fmt.Printf("Task ID: %s \n", getResp.ID) fmt.Printf("Model: %s \n", getResp.Model) fmt.Printf("Video URL: %s \n", getResp.Content.Or(model.TaskContent{}).VideoURL.Or("")) fmt.Printf("Completion Tokens: %d \n", getResp.Usage.Or(model.TaskUsage{}).CompletionTokens) fmt.Printf("Created At: %d, Updated At: %d", getResp.CreatedAt.Or(0), getResp.UpdatedAt.Or(0)) return } else if status == "failed" { fmt.Println("----- task failed -----") if getResp.Error.IsSet() { fmt.Printf("Error Code: %s, Message: %s", getResp.Error.Value.Code, getResp.Error.Value.Message) } return } else { fmt.Printf("Current status: %s, Retrying in 3 seconds... \n", status) time.Sleep(3 * time.Second) } } } ``` * [视频生成教程](/docs/video-generation-tutorial)：学习如何使用模型的视频生成能力，包括文本生成视频、首尾帧生视频、首帧生成视频等。 * [Doubao Seedance 2.5 提示词指南](/docs/seedance-2-5-prompt-guide)：使用生视频模型时，如何编写提示词。 ## 工具使用 通过工具/插件让模型具体读取外部数据及函数的能力，包括 * 内置工具：联网搜索、图片处理、知识库检索等已集成至方舟平台的工具。 * 三方工具：兼容 MCP 的三方工具。 * 自定义工具：您自行定义及开发的工具。 |输入 |输出预览 | | --- | --- | |What's the weather like in Beijing? |According to the latest weather data as of March 10, 2026, the current weather in Beijing is sunny with a gentle wind (less than level 3). The temperature around 11:30 AM is approximately 9°C, and it is expected to reach a high of 12°C during the day. The weather will remain clear at night with a low temperature of 1°C. | \ | |**Source**: Weather forecasts updated on March 10, 2026, from the Central Meteorological Observatory. | \ | |**Note: Data is accurate as of the latest available update at 05:30 AM on March 10.** | **选项：Python** ```Python import os from arkruntime import Ark client = Ark( base_url="https://ark.cn-beijing.volces.com/api/v3", api_key=os.getenv("ARK_API_KEY"), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input=[{"role": "user", "content": "What's the weather like in Beijing?"}], tools=[ { "type": "web_search", "max_keyword": 2, } ], stream=False, ) for item in response.output: if item.type == "message": for content in item.content: if content.type == "output_text": print(content.text) ``` **选项：Curl** ```Bash curl https://ark.cn-beijing.volces.com/api/v3/responses \ -H "Authorization: Bearer $ARK_API_KEY" \ -H 'Content-Type: application/json' \ -d '{ "model": "doubao-seed-2-1-pro-260915", "stream": false, "tools": [ { "type": "web_search", "max_keyword": 2 } ], "input": [ { "role": "user", "content": [ { "type": "input_text", "text": "What is the weather like in Beijing?" } ] } ] }' ``` **选项：Java** ```Java package com.ark.sample; import com.fasterxml.jackson.core.JsonProcessingException; import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.JsonNode; import com.volcengine.ark.runtime.models.responses.*; import com.volcengine.ark.runtime.service.ArkService; import java.util.Arrays; import java.util.List; public class demo { public static ObjectMapper om = new ObjectMapper(); public demo() throws JsonProcessingException { } public static List buildTools() { WebSearchTool t = WebSearchTool.builder().maxKeyword(2).build(); System.out.println(Arrays.asList(t)); return Arrays.asList(t); } public static void main(String[] args) throws JsonProcessingException { String apiKey = System.getenv("ARK_API_KEY"); ArkService arkService = ArkService.builder().apiKey(apiKey) .baseUrl("https://ark.cn-beijing.volces.com/api/v3") .build(); ResponsesRequest req = ResponsesRequest.builder() .model("doubao-seed-2-1-pro-260915") .input(ResponsesInput.ofList(java.util.Arrays.asList(ItemEasyMessage.builder().role(MessageRole.USER).content( MessageContent.ofList(java.util.Arrays.asList(ContentItemText.builder().text("What's the weather like in Beijing?").build())) ).build()))) .tools(buildTools()) .build(); Response resp = arkService.createResponse(req); System.out.println(resp); arkService.shutdownExecutor(); } } ``` **选项：Go** ```Go package main import ( "context" "fmt" "os" "github.com/volcengine/ark-runtime-go/arkruntime" "github.com/volcengine/ark-runtime-go/arkruntime/model/responses" ) func main() { client := arkruntime.NewClientWithApiKey( os.Getenv("ARK_API_KEY"), arkruntime.WithBaseUrl("https://ark.cn-beijing.volces.com/api/v3"), ) request := &responses.ResponsesRequest{ Model: "doubao-seed-2-1-pro-260915", Input: responses.NewStringResponsesInput("What is the weather in Beijing today?"), Tools: []responses.Tool{ { OneOf: responses.NewWebSearchToolToolSum( responses.WebSearchTool{ Type: responses.WebSearchToolTypeWebSearch, MaxKeyword: responses.NewOptInt32(2), }, ), }, }, MaxToolCalls: responses.NewOptInt64(1), } response, err := client.CreateResponses(context.Background(), request) if err != nil { fmt.Printf("response error: %v\n", err) return } fmt.Printf("Response: %v\n", response) } ``` **选项：OpenAI SDK** ```Python import os from openai import OpenAI client = OpenAI( base_url="https://ark.cn-beijing.volces.com/api/v3", api_key=os.getenv("ARK_API_KEY"), ) response = client.responses.create( model="doubao-seed-2-1-pro-260915", input=[{"role": "user", "content": "What's the weather like in Beijing?"}], tools=[ { "type": "web_search", "max_keyword": 2, } ], stream=False, ) for item in response.output: if item.type == "message": for content in item.content: if content.type == "output_text": print(content.text) ``` * [工具调用](/docs/responses-api-tool-calling)：学习如何让模型使用内置工具，如网页搜索、知识库检索、豆包助手等能力。 * [Function Calling（函数调用）](/docs/function-calling)：学习如何让模型调用自定义的工具。 * [云部署 MCP / Remote MCP](/docs/mcp-remote-mcp)：学习如何让模型使用 MCP 服务。 # 5 下一步 现在您已经完成了首次方舟模型服务的 API 调用，您可以探索模型的更多能力，包括： * [模型列表](/docs/model-list)：快速浏览方舟提供的模型全集以及各个模型所具备的能力，快速根据您的实际场景匹配到合适的模型。 * [模型接入指南（LLM） - 标准流程](/docs/go-live-access-sop)：把方舟大模型接入生产环境的完整流程（参数配置、Harness 接入、突发流量爬坡、上线监控）。 * [模型接入指南（LLM） - 常见问题](/docs/go-live-faq)：接入 / 上线过程中的效果、可用性、接入配置、选型常见问题。 * [模型接入指南（LLM） - 性能评测](/docs/go-live-benchmark-guide)：上线前跑一次性能基线评测（TTFT / TPOT / E2E / 缓存命中率）。