# 产品简介

> 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。

<span id="01a681e5"></span>
# 快速调用

完成首次 API 调用，请参见 [快速入门](/docs/quick-start)

**选项：Python**

```Python
import os
from arkruntime import Ark

client = Ark(
    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'),
)

response = client.responses.create(
    model="doubao-seed-2-1-pro-260915",
    input="hello", # Replace with your prompt
    # thinking={"type": "disabled"}, # Manually disable deep thinking
)
print(response)
```

**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"
  }'
```

Windows CMD 环境下请将 `$ARK_API_KEY` 替换为 `%ARK_API_KEY%`，PowerShell 环境下替换为 `$env:ARK_API_KEY`。

**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.sample;

import com.volcengine.ark.runtime.service.ArkService;
import com.volcengine.ark.runtime.models.responses.*;
public class DemoSample {
    public static void main(String[] args) {
        // Get API Key: https://ark.volcengine.com/region:cn-beijing/apikey
        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")) // Replace with your prompt
                // .thinking(Thinking.builder().type(ThinkingMode.DISABLED).build()) // Manually disable deep thinking
                .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',
    # Get API Key: https://ark.volcengine.com/region:cn-beijing/apikey
    api_key=os.getenv('ARK_API_KEY'),
)

response = client.responses.create(
    model="doubao-seed-2-1-pro-260915",
    input="hello", # Replace with your prompt
    extra_body={
        # "thinking": {"type": "disabled"}, # Manually disable deep thinking
    },
)

print(response)
```

<span id="fc299dc6"></span>
# 浏览模型

完整模型列表：[模型列表](/docs/model-list)

**[Doubao Seedance 2.5](https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedance-2-5)**
豆包高性能视频生成模型
4~30 秒视频生成，全模态参考输入

**[Doubao Seed Evolving](https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seed-evolving)**
Seed 最新 Coding&Agent 模型
周级迭代，持续进化 Coding 与 Agent 能力

**[Doubao Seedream 5.0 pro](https://ark.volcengine.com/region:cn-beijing/model/detail?Id=doubao-seedream-5-0-pro)**
最新图像创作模型
编辑更可控、生产更落地、效果更自然

<span id="bfd5f286"></span>
# 基础使用

快速掌握模型使用规则、调用限制和常见场景示例。

[深度思考](/docs/deep-thinking)
先思考再回答，质量显著提升

[视频生成](/docs/video-generation-tutorial)
生成高清流畅的影视级视频

[图片理解](/docs/image-understanding)
接收图片，根据图片信息回复

[图片生成](/docs/seedream-4-0-5-0)
基于图文，生成高质量图片

[视频理解](/docs/video-understanding)
接收视频，根据视频信息回复

[联网搜索](/docs/web-search)
联网获取实时知识

[文档理解](/docs/document-understanding)
接收 PDF，根据文档信息回复

[函数调用](/docs/function-calling)
调用自定义工具，增强模型能力

<span id="238fb521"></span>
# 进阶使用

了解如何拓展模型能力、提升性能、降低成本

[续写模式](/docs/continuation-mode)
预填部分 `assistant` 消息内容，引导和控制模型输出

[批量推理](/docs/batch-inference)
大幅提升吞吐，降低成本，适合无需即时响应的任务

[视觉定位](/docs/grounding)
在图片中找到对应的目标，并返回目标的坐标

[上下文缓存](/docs/context-cache)
缓存固定上下文，减少重复计算开销，降低成本

[文件输入](/docs/file-api)
使用 File API 上传并预处理视频、图片、PDF

[云部署 MCP](/docs/mcp-remote-mcp)
调用各类垂直领域 MCP 工具，增强模型能力

[3D 生成](/docs/3d-generation)
快速生成具备多边形面片与 PBR 材质的高精度 3D 资产

[GUI Agent 能力](/docs/gui-task-processing)
在计算机等真实 GUI 环境中完成自动化任务