### C Example for OpenAI Multimodal API Setup

Source: https://docs.apimart.ai/cn/api-reference/texts/openai/responses

Initializes cURL for making a request to the OpenAI Multimodal Response API. Requires the OPENAI_API_KEY environment variable.

```c
#include <stdio.h>
#include <curl/curl.h>
#include <stdlib.h>

int main(void) {
    CURL *curl;
    CURLcode res;
    const char *api_key = getenv("OPENAI_API_KEY");

    curl_global_init(CURL_GLOBAL_DEFAULT);
    curl = curl_easy_init();

    if(curl) {

```

--------------------------------

### Video Generation with Camera Movement Instructions

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

This example shows how to incorporate camera movement commands like '[推进]' directly into the prompt to guide the video's perspective. It specifies a 768p resolution and 6-second duration.

```json
{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "[推进]一只猫咪在花园中奔跑，镜头缓缓推进特写",
  "duration": 6,
  "resolution": "768p"
}
```

--------------------------------

### Start and End Frame Video Generation Example

Source: https://docs.apimart.ai/cn/api-reference/videos/vidu-q3-pro/generation

Create videos using specified start and end frame images. Provide 'model', 'prompt', 'image_urls' with two URLs, and 'duration'. The 'aspect_ratio' parameter is not applicable here.

```json
{
  "model": "viduq3-pro",
  "prompt": "人物从站立缓缓坐下",
  "image_urls": [
    "https://example.com/first.jpg",
    "https://example.com/last.jpg"
  ],
  "duration": 8
}
```

--------------------------------

### Image-to-Video Generation Example (Single Image)

Source: https://docs.apimart.ai/cn/api-reference/videos/vidu-q3-pro/generation

Generate videos starting with a single provided image. Set 'model', 'prompt', 'image_urls' with one URL, 'duration', and 'resolution'. The 'aspect_ratio' parameter cannot be used with 'image_urls'.

```json
{
  "model": "viduq3-pro",
  "prompt": "人物缓缓转身微笑",
  "image_urls": ["https://example.com/photo.jpg"],
  "duration": 5,
  "resolution": "720p"
}
```

--------------------------------

### Dynamic Product Showcase Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/doubao/generation

Create a dynamic video showcasing a product using a provided image URL as the starting frame. This example uses the fast model and a square aspect ratio.

```json
{
  "model": "doubao-seedance-1-0-pro-fast",
  "prompt": "产品缓缓旋转展示，背景为纯白色，光线柔和",
  "image_urls": ["https://example.com/product.png"],
  "duration": 5,
  "aspect_ratio": "1:1"
}
```

--------------------------------

### Image URL Example for Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/veo3/generation

This example shows how to provide a list of image URLs for image-to-video generation. Note that the 'veo3.1-lite' model does not support this parameter.

```json
{
  "image_urls": ["https://example.com/image1.jpg", "https://example.com/image2.jpg"]
}
```

--------------------------------

### Good System Prompt Example

Source: https://docs.apimart.ai/cn/integrations/chat/anythingllm

An example of an effective system prompt that clearly defines the AI's role, response guidelines, and fallback behavior.

```text
你是一个专业的技术支持助手，专门帮助用户解决产品相关的技术问题。

回答时请遵循以下原则：
1. 基于提供的文档内容回答，如果文档中没有相关信息，请明确告知
2. 提供详细的步骤说明，必要时给出示例
3. 使用清晰、易懂的语言
4. 对于复杂问题，建议用户联系技术支持团队
```

--------------------------------

### Good Prompt Example in Python

Source: https://docs.apimart.ai/cn/integrations/chat/chatbox

This example demonstrates a well-structured prompt for generating Python code. It clearly specifies the function's requirements, including input, filtering logic, output format, and the need for comments and examples.

```python
Please help me write a Python function that does the following:
1. Accepts a list of strings as input
2. Filters out strings with a length less than 3
3. Returns the result sorted alphabetically
Please include detailed comments and example usage.
```

--------------------------------

### Custom System Prompt Example

Source: https://docs.apimart.ai/cn/integrations/chat/anythingllm

Customize the AI's role and behavior by defining a system prompt. This example sets the AI as a professional technical support engineer.

```text
你是一个专业的技术支持工程师，擅长解答关于产品的技术问题。
回答时请：
1. 保持专业和礼貌
2. 提供详细的步骤说明
3. 如果不确定，建议用户联系技术支持
```

--------------------------------

### Swift TTS Example

Source: https://docs.apimart.ai/cn/api-reference/audios/tts

This Swift example demonstrates making a POST request to the TTS API using URLSession and saving the audio data to the document directory.

```swift
import Foundation

let url = URL(string: "https://api.apimart.ai/v1/audio/speech")!

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")

let payload: [String: Any] = [
    "model": "gpt-4o-mini-tts",
    "input": "今天天气真好,适合出去散步。",
    "voice": "alloy",
    "response_format": "opus",
    "speed": 1.0
]

request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }

    if let data = data {
        let fileURL = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)[0]
            .appendingPathComponent("speech.opus")
        try? data.write(to: fileURL)
        print("Audio saved to \(fileURL)")
    }
}

task.resume()
```

--------------------------------

### Image with Roles Example

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.7-r2v/generation

Example of using an array of objects for image_with_roles, specifying roles like 'reference_image' or 'first_frame', and optionally including a reference voice URL.

```json
[
  {
    "url": "https://cdn.example.com/character.jpg",
    "role": "reference_image",
    "reference_voice": "https://cdn.example.com/voice_sample.mp3"
  },
  { "url": "https://cdn.example.com/start.jpg", "role": "first_frame" }
]
```

--------------------------------

### Full Parameters for Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.6/i2v-flash-generation

This example demonstrates a comprehensive request with all available parameters for video generation, including prompts, resolution, duration, and advanced settings.

```json
{
  "model": "wan2.6-i2v-flash",
  "prompt": "让图片中的人物微笑挥手，镜头缓缓推进",
  "image_urls": ["https://example.com/image.jpg"],
  "negative_prompt": "模糊, 低质量, 变形",
  "resolution": "1080p",
  "duration": 10,
  "seed": 12345,
  "prompt_extend": true,
  "shot_type": "multi",
  "audio": true,
  "watermark": false
}
```

--------------------------------

### Get User Balance (Swift)

Source: https://docs.apimart.ai/cn/api-reference/account/user-balance

Swift code snippet for fetching user balance. This is a partial example showing the API key setup. You would typically use `URLSession` to make the network request.

```swift
import Foundation

let apiKey = "sk-xxxxxxxxxxxxxxxxxxxxxx"

```

--------------------------------

### Video Generation with Audio

Source: https://docs.apimart.ai/cn/api-reference/videos/veo3/generation-official

Example demonstrating how to generate a video with an accompanying audio track by setting the 'generate_audio' parameter to true.

```json
{
  "model": "veo3.1-quality-official",
  "prompt": "a busy coffee shop with people chatting and barista making latte art",
  "duration": 8,
  "generate_audio": true,
  "aspect_ratio": "16:9"
}
```

--------------------------------

### Full Example: Image-to-Image Workflow

Source: https://docs.apimart.ai/cn/api-reference/uploads/images

This comprehensive Python script illustrates the complete image-to-image workflow, including API key setup and base URL configuration. It's designed to be a starting point for integrating APIMart's image generation capabilities.

```python
import requests
import time

API_KEY = "your-Apimart-key"
BASE_URL = "https://api.apimart.ai"


```

--------------------------------

### Basic Text-to-Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

Use this snippet for a simple text-to-video generation task. Specify the model and a descriptive prompt to get started.

```json
{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "一只可爱的猫咪在草地上奔跑，阳光明媚"
}
```

--------------------------------

### Text-to-Video Generation (Full Parameters)

Source: https://docs.apimart.ai/cn/api-reference/videos/veo3/generation-official

Example demonstrating text-to-video generation with a comprehensive set of parameters, including negative prompts, duration, aspect ratio, resolution, seed, audio generation, person generation, and prompt enhancement.

```json
{
  "model": "veo3.1-quality-official",
  "prompt": "a cinematic close-up of a ragdoll cat slowly walking through a sunlit living room",
  "negative_prompt": "blurry, low quality, watermark, text",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "seed": 12345,
  "generate_audio": true,
  "person_generation": "disallow",
  "enhance_prompt": true
}
```

--------------------------------

### Iterative Improvement Example

Source: https://docs.apimart.ai/cn/integrations/dev-tool/cline

Demonstrates an iterative approach to development using AI. Start with basic functionality, test, and then refine through subsequent prompts.

```plaintext
第一轮：创建用户模型
第二轮：基于刚才的模型，创建 CRUD 接口
第三轮：为这些接口添加权限验证
```

--------------------------------

### First Frame Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.7/generation

Generate video starting from a single provided image. The prompt guides the action and camera movement from the first frame.

```json
{
  "model": "wan2.7",
  "prompt": "人物缓缓站起身，向镜头走来",
  "image_urls": ["https://cdn.example.com/person.jpg"],
  "resolution": "1080P",
  "duration": 8
}
```

--------------------------------

### Image-to-Video Generation (Multiple Image References)

Source: https://docs.apimart.ai/cn/api-reference/videos/kling-video-o1/generation

Example demonstrating how to reference multiple images in the prompt using '<<<image_N>>>' syntax for video generation. The 'pro' mode is specified for higher quality.

```json
{
  "model": "kling-video-o1",
  "prompt": "<<<image_1>>>中的角色走向<<<image_2>>>中的场景",
  "image_urls": [
    "https://example.com/character.jpg",
    "https://example.com/scene.jpg"
  ],
  "mode": "pro",
  "duration": 5
}
```

--------------------------------

### Generate Video with C#

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.5/generation

Example of how to generate a video using the wan2.5-preview model with a C# client. Ensure you replace '<token>' with your actual API key.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            "model": "wan2.5-preview",
            "prompt": "夕阳下的海边公路，电影感镜头",
            "size": "16:9",
            "resolution": "720p",
            "duration": 5
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

--------------------------------

### Generate Image with Gemini-3-Pro (OCaml)

Source: https://docs.apimart.ai/cn/api-reference/images/gemini-3-pro/generation

Example of how to generate an image using the Gemini-3-Pro model with OCaml. Ensure you have the necessary libraries like Cohttp-lwt and Lwt_main installed.

```OCaml
let () =
  let headers = Header.init () 
    |> fun h -> Header.add h "Authorization" "Bearer <token>"
    |> fun h -> Header.add h "Content-Type" "application/json"
  in
  let body = Cohttp_lwt.Body.of_string payload in
  
  let response = Client.post ~headers ~body (Uri.of_string url) >>= fun (resp, body) ->
    body |> Cohttp_lwt.Body.to_string >|= fun body_str ->
    print_endline body_str
  in
  Lwt_main.run response
```

--------------------------------

### Send a message to Claude

Source: https://docs.apimart.ai/cn/api-reference/texts/general/claude-messages

This example demonstrates how to send a message to the Claude API to get a response. It includes setting the API key, model, and message content.

```APIDOC
## POST /v1/messages

### Description
Sends a message to the Claude API to receive a response.

### Method
POST

### Endpoint
https://api.apimart.ai/v1/messages

### Parameters
#### Headers
- **x-api-key** (string) - Required - Your API key for authentication.
- **anthropic-version** (string) - Required - The version of the Anthropic API to use (e.g., "2025-10-01").
- **Content-Type** (string) - Required - Specifies the content type of the request body, typically "application/json".

#### Request Body
- **model** (string) - Required - The name of the Claude model to use (e.g., "claude-sonnet-4-5-20250929").
- **max_tokens** (integer) - Required - The maximum number of tokens to generate in the response.
- **messages** (array) - Required - An array of message objects, where each object has a "role" (user or assistant) and "content" (the message text).
  - **role** (string) - Required - The role of the message sender (e.g., "user").
  - **content** (string) - Required - The text of the message.

### Request Example
```json
{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "你好，世界"
    }
  ]
}
```

### Response
#### Success Response (200)
- **content** (array) - The response content from the model.
- **role** (string) - The role of the response sender (e.g., "assistant").
- **stop_reason** (string) - The reason the model stopped generating text (e.g., "end_turn").
- **model** (string) - The name of the model that generated the response.
- **usage** (object) - Information about token usage.
  - **input_tokens** (integer) - The number of input tokens.
  - **output_tokens** (integer) - The number of output tokens.

#### Response Example
```json
{
  "content": [
    {
      "type": "text",
      "text": "你好！有什么可以帮您的吗？"
    }
  ],
  "role": "assistant",
  "stop_reason": "end_turn",
  "model": "claude-sonnet-4-5-20250929",
  "usage": {
    "input_tokens": 15,
    "output_tokens": 18
  }
}
```
```

--------------------------------

### Query H5 Authentication Link

Source: https://docs.apimart.ai/cn/api-reference/videos/doubao-seedance-2-0/real-avatar

Example HTTP GET request to retrieve the H5 authentication link using the task ID obtained from session creation.

```http
GET /v1/tasks/task_01K...
```

--------------------------------

### Generate Video with Swift

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.5/generation

Example of how to generate a video using the wan2.5-preview model with a Swift client. Ensure you replace '<token>' with your actual API key.

```swift
import Foundation

let url = URL(string: "https://api.apimart.ai/v1/videos/generations")!

let payload: [String: Any] = [
    "model": "wan2.5-preview",
    "prompt": "夕阳下的海边公路，电影感镜头",
    "size": "16:9",
    "resolution": "720p",
    "duration": 5
]

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

let task = URLSession.shared.dataTask(with: request) {
    data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }

    if let data = data, let responseString = String(data: data, encoding: .utf8) {
        print(responseString)
    }
}

task.resume()
```

--------------------------------

### Video Generation Request Example with Camera Movement

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

This example demonstrates how to use camera movement instructions within the prompt to control the video's visual flow. Ensure the model and prompt are correctly specified.

```json
{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "[推进]一只猫咪在花园中奔跑，镜头缓缓推进特写"
}
```

--------------------------------

### System Prompt - String Format

Source: https://docs.apimart.ai/cn/api-reference/texts/general/claude-messages

Example of setting a system prompt using a simple string for defining the AI's role.

```json
{
  "system": "你是一位专业的Python编程导师"
}
```

--------------------------------

### cURL Request Example for Chat Completions

Source: https://apimart.ai/zh

This cURL command demonstrates how to make a POST request to the APIMart chat completions endpoint to get a response from a model like gpt-4o.

```curl
curl --request POST \
  --url https://api.apimart.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ \
    "model": "gpt-4o", \
    "messages": [ \
      { \
        "role": "system", \
        "content": "You are a professional AI assistant." \
      }, \
      { \
        "role": "user", \
        "content": "Tell me about the history of artificial intelligence." \
      } \
    ] \
  }'
```

--------------------------------

### Get Task Status using Swift

Source: https://docs.apimart.ai/cn/api-reference/tasks/status

Swift example for retrieving task status via `URLSession`. This code demonstrates setting the HTTP method and authorization header for the request.

```swift
import Foundation

let url = URL(string: "https://api.apimart.ai/v1/tasks/task-unified-1757156493-imcg5zqt?language=zh")!

var request = URLRequest(url: url)
request.httpMethod = "GET"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }
    
    if let data = data, let responseString = String(data: data, encoding: .utf8) {
        print(responseString)
    }
}

task.resume()
```

--------------------------------

### Get Task Status using Ruby

Source: https://docs.apimart.ai/cn/api-reference/tasks/status

Ruby code for fetching task status using the `net/http` library. This example shows how to set up the HTTP request, including the authorization header.

```ruby
require 'net/http'
require 'json'
require 'uri'

url = URI("https://api.apimart.ai/v1/tasks/task-unified-1757156493-imcg5zqt?language=zh")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = "Bearer <token>"

response = http.request(request)
puts response.body
```

--------------------------------

### Generate Video with MiniMax-Hailuo-2.3 (C#)

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

A C# example for video generation. It sets up an HttpClient, adds necessary headers, and sends the JSON payload. Remember to replace '<token>' with your API key.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            \"model\": \"MiniMax-Hailuo-2.3\",
            \"prompt\": \"一只可爱的猫咪在草地上奔跑\",
            \"duration\": 6,
            \"resolution\": \"768p\",
            \"prompt_optimizer\": true,
            \"fast_pretreatment\": false,
            \"watermark\": false
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

--------------------------------

### Get Task Status using Java

Source: https://docs.apimart.ai/cn/api-reference/tasks/status

Java code example for fetching task status using `java.net.http.HttpClient`. This snippet shows how to construct the request, set headers, and process the response.

```java
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;

public class Main {
    public static void main(String[] args) throws Exception {
        String url = "https://api.apimart.ai/v1/tasks/task-unified-1757156493-imcg5zqt?language=zh";

        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create(url))
            .header("Authorization", "Bearer <token>")
            .GET()
            .build();

        HttpResponse<String> response = client.send(request,
            HttpResponse.BodyHandlers.ofString());

        System.out.println(response.body());
    }
}
```

--------------------------------

### System Prompt - Structured Format

Source: https://docs.apimart.ai/cn/api-reference/texts/general/claude-messages

Example of setting a system prompt using a structured format with type and text for more detailed instructions.

```json
{
  "system": [
    {
      "type": "text",
      "text": "你是一位专业的Python编程导师"
    }
  ]
}
```

--------------------------------

### Pre-fill Assistant Response

Source: https://docs.apimart.ai/cn/api-reference/texts/general/claude-messages

Guide the model's response format by providing a partial assistant message. This is useful for ensuring the output starts in a specific way, like a numbered list.

```python
# 引导模型以特定格式回复
messages = [
    {"role": "user", "content": "列出5个Python最佳实践"},
    {"role": "assistant", "content": "以下是5个Python最佳实践：

1."}
]

message = client.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=1024,
    messages=messages
)
```

--------------------------------

### C# Example for OpenAI Multimodal API

Source: https://docs.apimart.ai/cn/api-reference/texts/openai/responses

Provides a C# example using HttpClient to call the OpenAI Multimodal Response API. Ensure the OPENAI_API_KEY is set as an environment variable.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/responses";
        var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");

        var payload = @"{ 
            "model": "gpt-5",
            "input": [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "input_text",
                            "text": "这张图片里有什么？"
                        },
                        {
                            "type": "input_image",
                            "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                        }
                    ]
                }
            ]
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", $"Bearer {apiKey}");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}

```

--------------------------------

### Single Image to Video Generation Request

Source: https://docs.apimart.ai/cn/api-reference/videos/omni-flash-ext/generation

Example request body for generating a video based on a single reference image and a text prompt. The prompt guides the action and camera motion.

```json
{
  "model": "Omni-Flash-Ext",
  "prompt": "make the character smile and slowly turn around, cinematic camera motion",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "9:16",
  "image_urls": ["https://example.com/character.jpg"]
}
```

--------------------------------

### Good Prompt Example for Performance Optimization

Source: https://docs.apimart.ai/cn/integrations/dev-tool/cursor

Provides a clear and actionable prompt for optimizing function performance, specifying key areas for improvement.

```text
优化这个函数的性能，重点关注：
1. 减少循环嵌套
2. 使用更高效的数据结构
3. 添加缓存机制
```

--------------------------------

### Fast Pre-treatment Mode for Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

Enable `fast_pretreatment` to potentially speed up prompt optimization at the cost of a slight reduction in optimization quality. This example also sets a 10-second duration and 768p resolution.

```json
{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "海浪拍打沙滩，日落时分",
  "duration": 10,
  "resolution": "768p",
  "prompt_optimizer": true,
  "fast_pretreatment": true
}
```

--------------------------------

### Three Reference Images Fusion for Video Generation

Source: https://docs.apimart.ai/cn/api-reference/videos/omni-flash-ext/generation

Example request body for generating a video by fusing elements from three reference images. This allows for complex scene composition guided by the prompt.

```json
{
  "model": "Omni-Flash-Ext",
  "prompt": "a creative scene combining these elements with smooth camera motion",
  "duration": 10,
  "resolution": "1080p",
  "aspect_ratio": "9:16",
  "image_urls": [
    "https://example.com/scene.jpg",
    "https://example.com/character.jpg",
    "https://example.com/product.jpg"
  ]
}
```

--------------------------------

### Python Integration Example

Source: https://apimart.ai/zh

This section outlines the three simple steps to integrate APIMart APIs into your application: registering for an API key, modifying the configuration to use the APIMart endpoint, and starting to call models.

```text
1
注册，创建密钥注册账户并在仪表板中生成您的专属 API 密钥，无需信用卡即可开始
获取 API 密钥查看文档
  2
修改配置将API端点更改为 APIMart 地址，OpenAI SDK 用户只需修改一行代码
查看文档在线试用
  3
开始调用模型通过统一接口访问 GPT-5、Claude、Sora 等数百种AI模型，即刻开启AI之旅
```

--------------------------------

### Generate Video with Kling v3 (JavaScript)

Source: https://docs.apimart.ai/cn/api-reference/videos/kling-v3/generation

This JavaScript example shows how to use the `fetch` API to send a POST request for video generation. It includes setting the necessary headers and handling the JSON response.

```javascript
const url = "https://api.apimart.ai/v1/videos/generations";

const payload = {
  model: "kling-v3",
  prompt: "一只金色的猫咪在阳光下的草地上奔跑，慢动作，电影质感",
  mode: "std",
  duration: 5,
  size: "16:9"
};

const headers = {
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(payload)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));
```

--------------------------------

### Get Task Status using JavaScript (Fetch API)

Source: https://docs.apimart.ai/cn/api-reference/tasks/status

Example of retrieving task status in JavaScript using the Fetch API. This code snippet shows how to configure the request with the correct method, headers, and URL.

```javascript
const url = "https://api.apimart.ai/v1/tasks/task-unified-1757156493-imcg5zqt?language=zh";

const headers = {
  "Authorization": "Bearer <token>"
};

fetch(url, {
  method: "GET",
  headers: headers
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));
```

--------------------------------

### Generate Video with MiniMax-Hailuo-02 (C#)

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo/generation

This C# example shows how to make a POST request to the video generation API. It uses HttpClient to send the JSON payload and includes necessary headers.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            \"model\": \"MiniMax-Hailuo-02\",
            \"prompt\": \"一只可爱的猫咪在草地上奔跑\",
            \"duration\": 5,
            \"resolution\": \"768p\",
            \"prompt_optimizer\": true,
            \"fast_pretreatment\": false,
            \"watermark\": false
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

--------------------------------

### Video Generation with First Frame Image

Source: https://docs.apimart.ai/cn/api-reference/videos/minimax-hailuo-2.3/generation

Specify a starting frame for your video by providing a public URL or Base64 encoded image in the `first_frame_image` parameter. This example also sets 1080p resolution and 6-second duration.

```json
{
  "model": "MiniMax-Hailuo-2.3",
  "prompt": "小猫跑向镜头，微笑着眨眼",
  "first_frame_image": "https://example.com/cat.jpg",
  "duration": 6,
  "resolution": "1080p"
}
```

--------------------------------

### Generate Video with Wan2.6 (C#)

Source: https://docs.apimart.ai/cn/api-reference/videos/wan2.6/generation

Example of making a POST request to generate a video using the Wan2.6 model in C#. Ensure you replace '<token>' with your actual API key.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            "model": "wan2.6",
            "prompt": "一只可爱的猫咪在草地上奔跑",
            "aspect_ratio": "16:9",
            "resolution": "720p",
            "duration": 5
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}

```

--------------------------------

### Web Search Tool Usage Example

Source: https://docs.apimart.ai/cn/api-reference/texts/openai/responses

This example shows how to use the web search tool with a text input. The model will use web search to find relevant information.

```json
{
  "model": "gpt-5",
  "tools": [{"type": "web_search"}],
  "input": "今天有什么正面的新闻？"
}
```

```bash
curl "https://api.apimart.ai/v1/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer <token>" \
    -d '{
        "model": "gpt-5",
        "tools": [{"type": "web_search"}],
        "input": "今天有什么正面的新闻？"
    }'
```

--------------------------------

### Generate Video with Kling Video O1 (C#)

Source: https://docs.apimart.ai/cn/api-reference/videos/kling-video-o1/generation

This C# code example shows how to generate a video using the Kling Video O1 model with `HttpClient`. Ensure you replace '<token>' with your API key and handle potential errors.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            ""model"": ""kling-video-o1"",
            ""prompt"": ""让<<<image_1>>>中的人物向镜头挥手"",
            ""image_urls"": [""https://upload.apimart.ai/f/models/9998230426123070-e9d6af04-cb5e-4731-8ae7-abf144cb0d29-9998230586368386-29641169-f698-4ab9-9b6d-380899e6521e-9998230593110693-c1741a3a-.webp""],
            ""mode"": ""std"",
            ""duration"": 5,
            ""aspect_ratio"": ""16:9""
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

--------------------------------

### Install Dependencies with Cline

Source: https://docs.apimart.ai/cn/integrations/dev-tool/cline

Leverage Cline to install project dependencies via the terminal. Specify the packages to be installed.

```text
安装 axios 和 dotenv 包
```

--------------------------------

### Generate Image with GPT-Image-2 (C#)

Source: https://docs.apimart.ai/cn/api-reference/images/gpt-image-2/generation

This C# example demonstrates how to make an asynchronous POST request to the image generation API. Remember to substitute '<token>' with your API key.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/images/generations";

        var payload = @"{ 
            \"model\": \"gpt-image-2\",
            \"prompt\": \"一只橘猫坐在窗台上看夕阳，水彩画风格\",
            \"n\": 1,
            \"size\": \"16:9\",
            \"resolution\": \"2k\"
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}

```

--------------------------------

### Verify Claude Code Installation

Source: https://docs.apimart.ai/cn/integrations/dev-tool/claude-code

Checks if the Claude Code CLI has been installed successfully by displaying its version number. Run this command after installation.

```bash
claude --version
```

--------------------------------

### Install Claude Code CLI via Homebrew (macOS)

Source: https://docs.apimart.ai/cn/integrations/dev-tool/claude-code

Installs the Claude Code CLI using Homebrew on macOS. This is an alternative installation method for macOS users.

```bash
brew install --cask claude-code
```

--------------------------------

### Swift Example for OpenAI Multimodal API

Source: https://docs.apimart.ai/cn/api-reference/texts/openai/responses

Illustrates making a multimodal API call using Swift's URLSession. The API key should be provided via the environment variable OPENAI_API_KEY.

```swift
import Foundation

let url = URL(string: "https://api.apimart.ai/v1/responses")!
let apiKey = ProcessInfo.processInfo.environment["OPENAI_API_KEY"] ?? ""

let payload: [String: Any] = [
    "model": "gpt-5",
    "input": [
        [
            "role": "user",
            "content": [
                [
                    "type": "input_text",
                    "text": "这张图片里有什么？"
                ],
                [
                    "type": "input_image",
                    "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                ]
            ]
        ]
    ]
]

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error: \(error)")
        return
    }
    
    if let data = data, let responseString = String(data: data, encoding: .utf8) {
        print(responseString)
    }
}

task.resume()

```

--------------------------------

### Generate Video with Kling 2.6 (C#)

Source: https://docs.apimart.ai/cn/api-reference/videos/kling-v2-6/generation

Example of making an asynchronous POST request to the video generation API using C#. Replace '<token>' with your API key.

```csharp
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        var url = "https://api.apimart.ai/v1/videos/generations";

        var payload = @"{ 
            "model": "kling-v2-6",
            "prompt": "一只金色的猫咪在阳光下的草地上奔跑，慢动作，电影质感",
            "mode": "std",
            "duration": 5,
            "aspect_ratio": "16:9"
        }";

        using var client = new HttpClient();
        client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

        var content = new StringContent(payload, Encoding.UTF8, "application/json");
        var response = await client.PostAsync(url, content);
        var result = await response.Content.ReadAsStringAsync();

        Console.WriteLine(result);
    }
}
```

--------------------------------

### Install Claude Code CLI (Windows CMD)

Source: https://docs.apimart.ai/cn/integrations/dev-tool/claude-code

Installs the Claude Code CLI using the Command Prompt (CMD) on Windows. This provides an alternative installation command for Windows users.

```cmd
curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
```

--------------------------------

### API Response Example - Success (200)

Source: https://docs.apimart.ai/cn/api-reference/videos/kling-v3/generation

Example of a successful video generation request response.

```json
{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_xxxxxxxxxx"
    }
  ]
}

```