atlas-cloud

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Atlas Cloud API Integration Guide

Atlas Cloud API 集成指南

Atlas Cloud is an AI API aggregation platform that provides access to 300+ image, video, and LLM models through a unified interface. This skill helps you quickly integrate Atlas Cloud API into any project.

Atlas Cloud是一个AI API聚合平台，通过统一接口提供300+图像、视频及LLM模型的访问能力。本技能可帮助你快速将Atlas Cloud API集成到任意项目中。

Quick Start

快速开始

1. Get an API Key

1. 获取API密钥

Create an API Key at Atlas Cloud Console.

在Atlas Cloud控制台创建API密钥。

2. Set Environment Variable

2. 设置环境变量

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

API Architecture

API架构

Atlas Cloud has the following API endpoints:

Endpoint	Base URL	Purpose
Media Generation API	`https://api.atlascloud.ai/api/v1`	Image generation, video generation, poll results, upload media
LLM API	`https://api.atlascloud.ai/v1`	Chat completions (OpenAI-compatible)

All requests require the following headers:

Authorization: Bearer $ATLASCLOUD_API_KEY
Content-Type: application/json

Atlas Cloud包含以下API端点：

端点	基础URL	用途
媒体生成API	`https://api.atlascloud.ai/api/v1`	图像生成、视频生成、查询结果、上传媒体
LLM API	`https://api.atlascloud.ai/v1`	对话补全（兼容OpenAI）

所有请求需包含以下请求头：

Authorization: Bearer $ATLASCLOUD_API_KEY
Content-Type: application/json

Full Endpoint List

完整端点列表

Method	Endpoint	Description
`POST`	`/api/v1/model/generateImage`	Submit image generation task
`POST`	`/api/v1/model/generateVideo`	Submit video generation task
`GET`	`/api/v1/model/prediction/{id}`	Check generation task status and result
`POST`	`/api/v1/model/uploadMedia`	Upload local media file to get a public URL
`POST`	`/v1/chat/completions`	LLM chat (OpenAI-compatible format)
`GET`	`api.atlascloud.ai/api/v1/models`	List all available models (no auth required)

方法	端点	描述
`POST`	`/api/v1/model/generateImage`	提交图像生成任务
`POST`	`/api/v1/model/generateVideo`	提交视频生成任务
`GET`	`/api/v1/model/prediction/{id}`	检查生成任务状态及结果
`POST`	`/api/v1/model/uploadMedia`	上传本地媒体文件以获取公共URL
`POST`	`/v1/chat/completions`	LLM对话（兼容OpenAI格式）
`GET`	`api.atlascloud.ai/api/v1/models`	列出所有可用模型（无需认证）

MCP Tools (9 Tools)

MCP工具（9个工具）

If the user has installed the Atlas Cloud MCP Server (

npx atlascloud-mcp

), the following 9 tools are available for direct invocation:

若用户已安装Atlas Cloud MCP Server（

npx atlascloud-mcp

），则可直接调用以下9个工具：

Model Discovery Tools

模型发现工具

atlas_list_models

— List All Models

atlas_list_models

— 列出所有模型

Params:
```
type
```
(optional):
```
"Text"
```
|
```
"Image"
```
|
```
"Video"
```
Purpose: List all available models, optionally filtered by type
Examples: No params to list all;
```
type="Image"
```
for image models only

参数：
```
type
```
（可选）：
```
"Text"
```
|
```
"Image"
```
|
```
"Video"
```
用途：列出所有可用模型，可按类型筛选
示例：无参数则列出全部；
```
type="Image"
```
仅列出图像模型

atlas_search_docs

— Search Models & Docs

atlas_search_docs

— 搜索模型与文档

Params:
```
query
```
(required): Search keyword matching model names, types, providers, tags
Purpose: Fuzzy search models by keyword. Returns detailed API schema info when there's only one match

Examples:

"video generation"

"deepseek"

"image edit"

"qwen"

参数：
```
query
```
（必填）：匹配模型名称、类型、提供商、标签的搜索关键词
用途：按关键词模糊搜索模型。若仅匹配到一个结果，返回详细的API schema信息

示例：

"video generation"

"deepseek"

"image edit"

"qwen"

atlas_get_model_info

— Get Model Details

atlas_get_model_info

— 获取模型详情

Params:
```
model
```
(required): Model ID, e.g.
```
"deepseek-ai/deepseek-v3.2"
```
Purpose: Get full model info including API docs, input/output schema, pricing, cURL examples, Playground link
Examples:
```
model="deepseek-ai/deepseek-v3.2"
```

参数：
```
model
```
（必填）：模型ID，例如
```
"deepseek-ai/deepseek-v3.2"
```
用途：获取完整模型信息，包括API文档、输入输出schema、定价、cURL示例、Playground链接
示例：
```
model="deepseek-ai/deepseek-v3.2"
```

Generation Tools

生成工具

atlas_generate_image

— Generate Image

atlas_generate_image

— 生成图像

Params:
- ```
model
```
  (required): Exact image model ID
- ```
params
```
  (required): Model-specific parameter JSON object (e.g.
```
prompt
```
  ,
```
image_size
```
  , etc.)
Purpose: Submit image generation task, returns prediction ID. Must verify model ID first via
```
atlas_list_models
```
or
```
atlas_search_docs
```
Returns: prediction ID — use
```
atlas_get_prediction
```
to check result

参数：
- ```
model
```
  （必填）：准确的图像模型ID
- ```
params
```
  （必填）：模型专属参数JSON对象（如
```
prompt
```
  、
```
image_size
```
  等）
用途：提交图像生成任务，返回预测ID。必须先通过
```
atlas_list_models
```
或
```
atlas_search_docs
```
验证模型ID
返回值：预测ID — 使用
```
atlas_get_prediction
```
检查结果

atlas_generate_video

— Generate Video

atlas_generate_video

— 生成视频

Params:
- ```
model
```
  (required): Exact video model ID
- ```
params
```
  (required): Model-specific parameter JSON object (e.g.
```
prompt
```
  ,
```
duration
```
  ,
```
aspect_ratio
```
  ,
```
image_url
```
  , etc.)
Purpose: Submit video generation task, returns prediction ID
Returns: prediction ID — video generation typically takes 1-5 minutes

参数：
- ```
model
```
  （必填）：准确的视频模型ID
- ```
params
```
  （必填）：模型专属参数JSON对象（如
```
prompt
```
  、
```
duration
```
  、
```
aspect_ratio
```
  、
```
image_url
```
  等）
用途：提交视频生成任务，返回预测ID
返回值：预测ID — 视频生成通常需要1-5分钟

atlas_quick_generate

— Quick Generate (One-Step)

atlas_quick_generate

— 一键快速生成

Params:
- ```
model_keyword
```
  (required): Model search keyword, e.g.
```
"nano banana"
```
  ,
```
"seedream"
```
  ,
```
"kling v3"
```
- ```
type
```
  (required):
```
"Image"
```
  |
```
"Video"
```
- ```
prompt
```
  (required): Text description of what to generate
- ```
image_url
```
  (optional): Source image URL for image-to-video or image editing models
- ```
extra_params
```
  (optional): Additional model-specific parameters to override defaults
Purpose: One-step generation — automatically searches model → fetches schema → builds params → submits task. No need to know exact model IDs

Examples:

model_keyword="seedream v5", type="Image", prompt="a cute cat"

参数：
- ```
model_keyword
```
  （必填）：模型搜索关键词，例如
```
"nano banana"
```
  ,
```
"seedream"
```
  ,
```
"kling v3"
```
- ```
type
```
  （必填）：
```
"Image"
```
  |
```
"Video"
```
- ```
prompt
```
  （必填）：生成内容的文本描述
- ```
image_url
```
  （可选）：图生视频或图像编辑模型的源图像URL
- ```
extra_params
```
  （可选）：覆盖默认值的额外模型专属参数
用途：一键生成 — 自动搜索模型→获取schema→构建参数→提交任务。无需知晓准确模型ID

示例：

model_keyword="seedream v5", type="Image", prompt="a cute cat"

atlas_chat

— LLM Chat

atlas_chat

— LLM对话

Params:
- ```
model
```
  (required): LLM model ID
- ```
messages
```
  (required): Array of message objects with
```
role
```
  and
```
content
```
- ```
temperature
```
  (optional): Sampling temperature 0-2
- ```
max_tokens
```
  (optional): Maximum response tokens
- ```
top_p
```
  (optional): Nucleus sampling parameter 0-1
Purpose: Send OpenAI-compatible chat completion request

参数：
- ```
model
```
  （必填）：LLM模型ID
- ```
messages
```
  （必填）：包含
```
role
```
  和
```
content
```
  的消息对象数组
- ```
temperature
```
  （可选）：采样温度0-2
- ```
max_tokens
```
  （可选）：最大响应令牌数
- ```
top_p
```
  （可选）：核采样参数0-1
用途：发送兼容OpenAI格式的对话补全请求

Utility Tools

实用工具

atlas_get_prediction

— Check Generation Result

atlas_get_prediction

— 检查生成结果

Params:
```
prediction_id
```
(required): Prediction ID returned from a generation request
Purpose: Check image/video generation task status and result

Status values:

starting

→

processing

→

completed

succeeded

failed

On completion: Returns output URL list — can download locally via curl/wget

参数：
```
prediction_id
```
（必填）：生成请求返回的预测ID
用途：检查图像/视频生成任务的状态及结果

状态值：

starting

→

processing

→

completed

succeeded

failed

完成后：返回输出URL列表 — 可通过curl/wget本地下载

atlas_upload_media

— Upload Media File

atlas_upload_media

— 上传媒体文件

Params:
```
file_path
```
(required): Absolute path to the local file
Purpose: Upload local image/media file to Atlas Cloud and get a publicly accessible URL. Use this to provide
```
image_url
```
for image editing or image-to-video models
Workflow:
1. Upload local file with this tool to get a URL
2. Use the returned URL as the
```
image_url
```
  parameter for
```
atlas_generate_image
```
  ,
```
atlas_generate_video
```
  , or
```
atlas_quick_generate
```
Note: Only for Atlas Cloud generation tasks. Uploaded files are temporary and will be cleaned up periodically. Uploading content unrelated to generation tasks (e.g., bulk hosting, illegal content, or abuse) may result in API key suspension

参数：
```
file_path
```
（必填）：本地文件的绝对路径
用途：将本地图像/媒体文件上传至Atlas Cloud并获取可公开访问的URL。用于为图像编辑或图生视频模型提供
```
image_url
```
参数
流程：
1. 使用本工具上传本地文件以获取URL
2. 将返回的URL作为
```
image_url
```
  参数传入
```
atlas_generate_image
```
  、
```
atlas_generate_video
```
  或
```
atlas_quick_generate
```
注意：仅适用于Atlas Cloud生成任务。上传的文件为临时文件，会定期清理。上传与生成任务无关的内容（如批量托管、非法内容或滥用）可能导致API密钥被暂停使用

Image Generation

图像生成

Image generation is an asynchronous two-step process: submit task → poll result.

图像生成是异步两步流程：提交任务 → 查询结果。

Submit Image Generation Task

提交图像生成任务

POST https://api.atlascloud.ai/api/v1/model/generateImage

Request body:

json

{
  "model": "bytedance/seedream-v5.0-lite",
  "prompt": "A beautiful sunset over mountains",
  "image_size": "1024x1024"
}

Response:

json

{
  "code": 200,
  "data": {
    "id": "prediction_abc123",
    "status": "starting"
  }
}

Different models accept different parameters. Common parameters include:

```
prompt
```
(required): Image description
```
image_size
```
/
```
width
```
+
```
height
```
: Dimensions
```
num_inference_steps
```
: Inference steps
```
guidance_scale
```
: Guidance scale
```
image_url
```
: Input image (for image-to-image models)

POST https://api.atlascloud.ai/api/v1/model/generateImage

请求体：

json

{
  "model": "bytedance/seedream-v5.0-lite",
  "prompt": "A beautiful sunset over mountains",
  "image_size": "1024x1024"
}

响应：

json

{
  "code": 200,
  "data": {
    "id": "prediction_abc123",
    "status": "starting"
  }
}

不同模型接受不同参数，常见参数包括：

```
prompt
```
（必填）：图像描述
```
image_size
```
/
```
width
```
+
```
height
```
：尺寸
```
num_inference_steps
```
：推理步数
```
guidance_scale
```
：引导系数
```
image_url
```
：输入图像（适用于图生图模型）

Poll Generation Result

查询生成结果

GET https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}

Response:

json

{
  "code": 200,
  "data": {
    "id": "prediction_abc123",
    "status": "completed",
    "outputs": ["https://cdn.atlascloud.ai/generated/xxx.png"]
  }
}

Possible

status

values:

starting

→

processing

→

completed

failed

Image generation typically takes 10-30 seconds. Poll every 3 seconds.

GET https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}

响应：

json

{
  "code": 200,
  "data": {
    "id": "prediction_abc123",
    "status": "completed",
    "outputs": ["https://cdn.atlascloud.ai/generated/xxx.png"]
  }
}

可能的

status

值：

starting

→

processing

→

completed

failed

图像生成通常需要10-30秒，建议每3秒查询一次。

Video Generation

视频生成

Video generation follows the exact same flow as image generation, just with a different endpoint.

视频生成流程与图像生成完全一致，仅端点不同。

Submit Video Generation Task

提交视频生成任务

POST https://api.atlascloud.ai/api/v1/model/generateVideo

Request body:

json

{
  "model": "kwaivgi/kling-v3.0-std/text-to-video",
  "prompt": "A rocket launching into space",
  "duration": 5,
  "aspect_ratio": "16:9"
}

Common video model parameters:

```
prompt
```
(required): Video description
```
image_url
```
: Input image (for image-to-video models)
```
duration
```
: Video duration in seconds
```
aspect_ratio
```
: Aspect ratio (e.g.,
```
"16:9"
```
,
```
"9:16"
```
,
```
"1:1"
```
)

Poll results using the same prediction endpoint. Video generation typically takes 1-5 minutes.

POST https://api.atlascloud.ai/api/v1/model/generateVideo

请求体：

json

{
  "model": "kwaivgi/kling-v3.0-std/text-to-video",
  "prompt": "A rocket launching into space",
  "duration": 5,
  "aspect_ratio": "16:9"
}

常见视频模型参数：

```
prompt
```
（必填）：视频描述
```
image_url
```
：输入图像（适用于图生视频模型）
```
duration
```
：视频时长（秒）
```
aspect_ratio
```
：宽高比（如
```
"16:9"
```
,
```
"9:16"
```
,
```
"1:1"
```
）

使用相同的预测端点查询结果。视频生成通常需要1-5分钟。

Upload Media

上传媒体

Upload a local file to Atlas Cloud to get a publicly accessible URL. This is required when you need to provide an

image_url

to image-editing or image-to-video models but only have a local file.

将本地文件上传至Atlas Cloud以获取可公开访问的URL。当你需要为图像编辑或图生视频模型提供

image_url

但仅有本地文件时，需使用此功能。

Upload Endpoint

上传端点

POST https://api.atlascloud.ai/api/v1/model/uploadMedia
Content-Type: multipart/form-data
Authorization: Bearer $ATLASCLOUD_API_KEY

Request: multipart form data with a

file

field containing the file binary.

Response:

json

{
  "code": 200,
  "data": {
    "download_url": "https://atlas-img.oss-accelerate-overseas.aliyuncs.com/media/xxx.jpg",
    "filename": "photo.jpg",
    "size": 123456
  }
}

POST https://api.atlascloud.ai/api/v1/model/uploadMedia
Content-Type: multipart/form-data
Authorization: Bearer $ATLASCLOUD_API_KEY

请求：包含

file

字段（文件二进制数据）的multipart表单数据。

响应：

json

{
  "code": 200,
  "data": {
    "download_url": "https://atlas-img.oss-accelerate-overseas.aliyuncs.com/media/xxx.jpg",
    "filename": "photo.jpg",
    "size": 123456
  }
}

Workflow: Local Image → Image-to-Video

流程：本地图像 → 图生视频

Upload local image → get URL
Use URL as
```
image_url
```
parameter in generation request

Important: This upload endpoint is strictly for temporary use with Atlas Cloud generation tasks. Uploaded files will be cleaned up periodically. Do NOT use this as permanent file hosting, CDN, or for any purpose unrelated to Atlas Cloud image/video generation. Abuse (e.g., bulk uploads, hosting illegal or unrelated content) may result in immediate API key suspension.

上传本地图像 → 获取URL
将URL作为生成请求中的
```
image_url
```
参数

重要提示：此上传端点仅可临时用于Atlas Cloud生成任务。上传的文件会定期清理。请勿将其用作永久文件托管、CDN或任何与Atlas Cloud图像/视频生成无关的用途。滥用行为（如批量上传、托管非法或无关内容）可能导致API密钥立即被暂停使用。

LLM Chat API (OpenAI-Compatible)

LLM对话API（兼容OpenAI）

The LLM API is fully compatible with the OpenAI format. You can use the OpenAI SDK directly.

POST https://api.atlascloud.ai/v1/chat/completions

Request body:

json

{
  "model": "qwen/qwen3.5-397b-a17b",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant"},
    {"role": "user", "content": "Hello!"}
  ],
  "max_tokens": 1024,
  "temperature": 0.7,
  "stream": false
}

Response (standard OpenAI format):

json

{
  "id": "chatcmpl-xxx",
  "model": "qwen/qwen3.5-397b-a17b",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "Hello! How can I help?"},
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 8,
    "total_tokens": 28
  }
}

LLM API完全兼容OpenAI格式，你可直接使用OpenAI SDK。

POST https://api.atlascloud.ai/v1/chat/completions

请求体：

json

{
  "model": "qwen/qwen3.5-397b-a17b",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant"},
    {"role": "user", "content": "Hello!"}
  ],
  "max_tokens": 1024,
  "temperature": 0.7,
  "stream": false
}

响应（标准OpenAI格式）：

json

{
  "id": "chatcmpl-xxx",
  "model": "qwen/qwen3.5-397b-a17b",
  "choices": [{
    "index": 0,
    "message": {"role": "assistant", "content": "Hello! How can I help?"},
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 8,
    "total_tokens": 28
  }
}

Using OpenAI SDK

使用OpenAI SDK

Since Atlas Cloud LLM API is fully OpenAI-compatible, you can use the official SDKs directly:

Python:

python

from openai import OpenAI

client = OpenAI(
    api_key="your-atlascloud-api-key",
    base_url="https://api.atlascloud.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-397b-a17b",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=1024
)
print(response.choices[0].message.content)

Node.js / TypeScript:

typescript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-atlascloud-api-key',
  baseURL: 'https://api.atlascloud.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'qwen/qwen3.5-397b-a17b',
  messages: [{ role: 'user', content: 'Hello!' }],
  max_tokens: 1024,
});
console.log(response.choices[0].message.content);

由于Atlas Cloud LLM API完全兼容OpenAI，你可直接使用官方SDK：

Python：

python

from openai import OpenAI

client = OpenAI(
    api_key="your-atlascloud-api-key",
    base_url="https://api.atlascloud.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.5-397b-a17b",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=1024
)
print(response.choices[0].message.content)

Node.js / TypeScript：

typescript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-atlascloud-api-key',
  baseURL: 'https://api.atlascloud.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'qwen/qwen3.5-397b-a17b',
  messages: [{ role: 'user', content: 'Hello!' }],
  max_tokens: 1024,
});
console.log(response.choices[0].message.content);

Code Templates

代码模板

For full implementation code with polling logic, error handling, and streaming support, read the reference files:

references/image-gen.md
— Complete image generation implementation (Python / Node.js / cURL)
references/video-gen.md
— Complete video generation implementation, including image-to-video
references/llm-chat.md
— LLM chat implementation with streaming support
references/upload.md
— Media file upload implementation (Python / Node.js / cURL)
references/quick-generate.md
— Quick generation with auto model search (Python / Node.js)
references/models.md
— Popular model ID quick reference

Read the corresponding reference file when you need to write specific integration code.

如需包含查询逻辑、错误处理和流式支持的完整实现代码，请参考以下参考文件：

references/image-gen.md
— 完整图像生成实现（Python / Node.js / cURL）
references/video-gen.md
— 完整视频生成实现，包括图生视频
references/llm-chat.md
— 支持流式的LLM对话实现
references/upload.md
— 媒体文件上传实现（Python / Node.js / cURL）
references/quick-generate.md
— 自动模型搜索的快速生成实现（Python / Node.js）
references/models.md
— 热门模型ID速查

当你需要编写特定集成代码时，请阅读对应的参考文件。

IMPORTANT: Always Verify Model IDs

重要提示：始终验证模型ID

Model IDs change frequently as new versions are released and old ones are deprecated. Unless you are 100% certain of an exact model ID, always fetch the real model list first before writing any integration code:

GET https://api.atlascloud.ai/api/v1/models

This endpoint requires no authentication and returns all currently available models with their exact IDs, types, and pricing. Never guess or fabricate model IDs — an incorrect model ID will cause API calls to fail.

Important: Only models with

display_console: true

are publicly available. Filter out models where

display_console

false

— those are internal and not accessible to regular users.

When writing code for the user, always include a step to verify the model ID exists, or fetch the list programmatically to pick the right one.

随着新版本发布和旧版本弃用，模型ID会频繁变更。除非你100%确定准确的模型ID，否则在编写任何集成代码前，务必先获取最新的模型列表：

GET https://api.atlascloud.ai/api/v1/models

此端点无需认证，返回所有当前可用模型的准确ID、类型和定价信息。切勿猜测或编造模型ID — 错误的模型ID会导致API调用失败。

重要提示：仅

display_console: true

的模型为公开可用。请过滤掉

display_console

为

false

的模型 — 这些是内部模型，普通用户无法访问。

为用户编写代码时，务必包含验证模型ID是否存在的步骤，或通过编程方式获取列表以选择正确的模型。

Popular Models (examples only — always verify via API)

Model ID	Name	Price
`google/nano-banana-2/text-to-image`	Nano Banana 2 Text-to-Image	$0.072/image
`google/nano-banana-2/text-to-image-developer`	Nano Banana 2 Developer	$0.056/image
`google/nano-banana-2/edit`	Nano Banana 2 Edit	$0.072/image
`bytedance/seedream-v5.0-lite`	Seedream v5.0 Lite	$0.032/image
`bytedance/seedream-v5.0-lite/edit`	Seedream v5.0 Lite Edit	$0.032/image
`alibaba/qwen-image/edit-plus-20251215`	Qwen-Image Edit Plus	$0.021/image
`z-image/turbo`	Z-Image Turbo	$0.01/image

模型ID	名称	价格
`google/nano-banana-2/text-to-image`	Nano Banana 2 文生图	$0.072/张
`google/nano-banana-2/text-to-image-developer`	Nano Banana 2 开发者版	$0.056/张
`google/nano-banana-2/edit`	Nano Banana 2 图像编辑	$0.072/张
`bytedance/seedream-v5.0-lite`	Seedream v5.0 Lite	$0.032/张
`bytedance/seedream-v5.0-lite/edit`	Seedream v5.0 Lite 图像编辑	$0.032/张
`alibaba/qwen-image/edit-plus-20251215`	Qwen-Image 高级编辑	$0.021/张
`z-image/turbo`	Z-Image Turbo	$0.01/张

Model ID	Name	Price
`kwaivgi/kling-v3.0-std/text-to-video`	Kling v3.0 Std Text-to-Video	$0.153/gen
`kwaivgi/kling-v3.0-std/image-to-video`	Kling v3.0 Std Image-to-Video	$0.153/gen
`kwaivgi/kling-v3.0-pro/text-to-video`	Kling v3.0 Pro Text-to-Video	$0.204/gen
`kwaivgi/kling-v3.0-pro/image-to-video`	Kling v3.0 Pro Image-to-Video	$0.204/gen
`bytedance/seedance-v1.5-pro/text-to-video`	Seedance v1.5 Pro Text-to-Video	$0.222/gen
`bytedance/seedance-v1.5-pro/image-to-video`	Seedance v1.5 Pro Image-to-Video	$0.222/gen
`vidu/q3/text-to-video`	Vidu Q3 Text-to-Video	$0.06/gen
`vidu/q3/image-to-video`	Vidu Q3 Image-to-Video	$0.06/gen
`alibaba/wan-2.6/image-to-video`	Wan-2.6 Image-to-Video	$0.07/gen

模型ID	名称	价格
`kwaivgi/kling-v3.0-std/text-to-video`	Kling v3.0 标准版文生视频	$0.153/次
`kwaivgi/kling-v3.0-std/image-to-video`	Kling v3.0 标准版图生视频	$0.153/次
`kwaivgi/kling-v3.0-pro/text-to-video`	Kling v3.0 专业版文生视频	$0.204/次
`kwaivgi/kling-v3.0-pro/image-to-video`	Kling v3.0 专业版图生视频	$0.204/次
`bytedance/seedance-v1.5-pro/text-to-video`	Seedance v1.5 专业版文生视频	$0.222/次
`bytedance/seedance-v1.5-pro/image-to-video`	Seedance v1.5 专业版图生视频	$0.222/次
`vidu/q3/text-to-video`	Vidu Q3 文生视频	$0.06/次
`vidu/q3/image-to-video`	Vidu Q3 图生视频	$0.06/次
`alibaba/wan-2.6/image-to-video`	Wan-2.6 图生视频	$0.07/次

Model ID	Name	Input	Output
`qwen/qwen3.5-397b-a17b`	Qwen3.5 397B A17B	$0.55/M	$3.5/M
`qwen/qwen3.5-122b-a10b`	Qwen3.5 122B A10B	$0.3/M	$2.4/M
`moonshotai/kimi-k2.5`	Kimi K2.5	$0.5/M	$2.6/M
`zai-org/glm-5`	GLM 5	$0.95/M	$3.15/M
`minimaxai/minimax-m2.5`	MiniMax M2.5	$0.295/M	$1.2/M
`deepseek-ai/deepseek-v3.2-speciale`	DeepSeek V3.2 Speciale	$0.4/M	$1.2/M
`qwen/qwen3-coder-next`	Qwen3 Coder Next	$0.18/M	$1.35/M

模型ID	名称	输入	输出
`qwen/qwen3.5-397b-a17b`	Qwen3.5 397B A17B	$0.55/百万令牌	$3.5/百万令牌
`qwen/qwen3.5-122b-a10b`	Qwen3.5 122B A10B	$0.3/百万令牌	$2.4/百万令牌
`moonshotai/kimi-k2.5`	Kimi K2.5	$0.5/百万令牌	$2.6/百万令牌
`zai-org/glm-5`	GLM 5	$0.95/百万令牌	$3.15/百万令牌
`minimaxai/minimax-m2.5`	MiniMax M2.5	$0.295/百万令牌	$1.2/百万令牌
`deepseek-ai/deepseek-v3.2-speciale`	DeepSeek V3.2 Speciale	$0.4/百万令牌	$1.2/百万令牌
`qwen/qwen3-coder-next`	Qwen3 Coder Next	$0.18/百万令牌	$1.35/百万令牌

Error Handling

错误处理

HTTP Status	Meaning	Suggested Action
401	Invalid or expired API Key	Check ATLASCLOUD_API_KEY
402	Insufficient balance	Top up at Billing Page
429	Rate limited	Wait and retry with exponential backoff
5xx	Server error	Wait and retry

HTTP状态码	含义	建议操作
401	API密钥无效或过期	检查ATLASCLOUD_API_KEY
402	余额不足	在账单页面充值
429	请求频率超限	等待后重试，使用指数退避策略
5xx	服务器错误	等待后重试

Retry Strategy

重试策略

GET requests: Auto retry up to 3 times with exponential backoff (1s → 2s → 4s)
POST requests: Do NOT retry — generation requests may create billable tasks, retrying could cause duplicate charges

GET请求：自动重试最多3次，使用指数退避（1秒 → 2秒 → 4秒）
POST请求：请勿重试 — 生成请求可能会产生计费任务，重试可能导致重复扣费

MCP Server Installation

MCP Server安装

Atlas Cloud MCP Server provides 9 tools for direct use in any MCP-compatible client. Prerequisites: Node.js >= 18 and an Atlas Cloud API Key.

Atlas Cloud MCP Server提供9个可直接在任意兼容MCP的客户端中使用的工具。前提条件：Node.js >= 18及Atlas Cloud API密钥。

CLI Tools (One-Line Install)

CLI工具（一键安装）

bash

undefined

bash

undefined

Claude Code

claude mcp add atlascloud -- npx -y atlascloud-mcp

Gemini CLI

gemini mcp add atlascloud -- npx -y atlascloud-mcp

OpenAI Codex CLI

codex mcp add atlascloud -- npx -y atlascloud-mcp

Goose CLI

goose mcp add atlascloud -- npx -y atlascloud-mcp


> For CLI tools, make sure to set the `ATLASCLOUD_API_KEY` environment variable in your shell:
> ```bash
> export ATLASCLOUD_API_KEY="your-api-key-here"
> ```

goose mcp add atlascloud -- npx -y atlascloud-mcp


> 对于CLI工具，请确保在shell中设置`ATLASCLOUD_API_KEY`环境变量：
> ```bash
> export ATLASCLOUD_API_KEY="your-api-key-here"
> ```

IDEs & Editors (JSON Config)

IDE与编辑器（JSON配置）

Add to your MCP configuration file — works with all MCP-compatible IDEs and editors:

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": ["-y", "atlascloud-mcp"],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Client	Config Location
Cursor	Settings → MCP → Add Server
Windsurf	Settings → MCP → Add Server
VS Code (Copilot)	`.vscode/mcp.json` or Settings → MCP
Trae	Settings → MCP → Add Server
Zed	Settings → MCP
JetBrains IDEs	Settings → Tools → AI Assistant → MCP
Claude Desktop	`claude_desktop_config.json`
ChatGPT Desktop	Settings → MCP
Amazon Q Developer	MCP Configuration

将以下内容添加到你的MCP配置文件中 — 适用于所有兼容MCP的IDE和编辑器：

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": ["-y", "atlascloud-mcp"],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

客户端	配置位置
Cursor	设置 → MCP → 添加服务器
Windsurf	设置 → MCP → 添加服务器
VS Code (Copilot)	`.vscode/mcp.json` 或设置 → MCP
Trae	设置 → MCP → 添加服务器
Zed	设置 → MCP
JetBrains IDEs	设置 → 工具 → AI助手 → MCP
Claude Desktop	`claude_desktop_config.json`
ChatGPT Desktop	设置 → MCP
Amazon Q Developer	MCP配置

VS Code Extensions

VS Code扩展

These VS Code extensions also support MCP with the same JSON config format:

Extension	Install
Cline	MCP Marketplace → Add Server
Roo Code	Settings → MCP → Add Server
Continue	`config.yaml` → MCP

以下VS Code扩展也支持MCP，使用相同的JSON配置格式：

扩展	安装方式
Cline	MCP Marketplace → 添加服务器
Roo Code	设置 → MCP → 添加服务器
Continue	`config.yaml` → MCP

Skills Version (Alternative)

技能版本（替代方案）

If you prefer using Skills instead of MCP:

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

若你偏好使用Skills而非MCP：

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

atlas-cloud

Original

Translation

Atlas Cloud API Integration Guide

Atlas Cloud API 集成指南

Quick Start

快速开始

1. Get an API Key

1. 获取API密钥

2. Set Environment Variable

2. 设置环境变量

API Architecture

API架构

Full Endpoint List

完整端点列表

MCP Tools (9 Tools)

MCP工具（9个工具）

Model Discovery Tools

模型发现工具

atlas_list_models — List All Models

atlas_list_models — 列出所有模型

atlas_search_docs — Search Models & Docs

atlas_search_docs — 搜索模型与文档

atlas_get_model_info — Get Model Details

atlas_get_model_info — 获取模型详情

Generation Tools

生成工具

atlas_generate_image — Generate Image

atlas_generate_image — 生成图像

atlas_generate_video — Generate Video

atlas_generate_video — 生成视频

atlas_quick_generate — Quick Generate (One-Step)

atlas_quick_generate — 一键快速生成

atlas_chat — LLM Chat

atlas_chat — LLM对话

Utility Tools

实用工具

atlas_get_prediction — Check Generation Result

atlas_get_prediction — 检查生成结果

atlas_upload_media — Upload Media File

atlas_upload_media — 上传媒体文件

Image Generation

图像生成

Submit Image Generation Task

提交图像生成任务

Poll Generation Result

查询生成结果

Video Generation

视频生成

Submit Video Generation Task

提交视频生成任务

Upload Media

上传媒体

Upload Endpoint

上传端点

Workflow: Local Image → Image-to-Video

流程：本地图像 → 图生视频

LLM Chat API (OpenAI-Compatible)

LLM对话API（兼容OpenAI）

Using OpenAI SDK

使用OpenAI SDK

Code Templates

代码模板

IMPORTANT: Always Verify Model IDs

重要提示：始终验证模型ID

Popular Models (examples only — always verify via API)

热门模型（仅作示例 — 请始终通过API验证）

Image Models (priced per image)

图像模型（按图像计费）

Video Models (priced per generation)

视频模型（按生成次数计费）

LLM Models (priced per million tokens)

LLM模型（按百万令牌计费）

Error Handling

错误处理

Retry Strategy

重试策略

MCP Server Installation

MCP Server安装

CLI Tools (One-Line Install)

`atlas_list_models`
— List All Models

`atlas_list_models`
— 列出所有模型

`atlas_search_docs`
— Search Models & Docs

`atlas_search_docs`
— 搜索模型与文档

`atlas_get_model_info`
— Get Model Details

`atlas_get_model_info`
— 获取模型详情

`atlas_generate_image`
— Generate Image

`atlas_generate_image`
— 生成图像

`atlas_generate_video`
— Generate Video

`atlas_generate_video`
— 生成视频

`atlas_quick_generate`
— Quick Generate (One-Step)

`atlas_quick_generate`
— 一键快速生成

`atlas_chat`
— LLM Chat

`atlas_chat`
— LLM对话

`atlas_get_prediction`
— Check Generation Result

`atlas_get_prediction`
— 检查生成结果

`atlas_upload_media`
— Upload Media File

`atlas_upload_media`
— 上传媒体文件