### Get All Tokens Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response detailing a token's properties, including its ID, session and access tokens, expiration, user information, and usage counts.

```json
[
  {
    "id": 1,
    "st": "session_token_value",
    "at": "access_token_value",
    "at_expires": "2025-01-15T04:46:04.000Z",
    "email": "user@example.com",
    "name": "User Name",
    "remark": "主账号",
    "is_active": true,
    "credits": 920,
    "current_project_id": "uuid-project-id",
    "current_project_name": "My Project",
    "image_enabled": true,
    "video_enabled": true,
    "image_concurrency": -1,
    "video_concurrency": -1,
    "image_count": 150,
    "video_count": 30,
    "error_count": 2
  }
]
```

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

### Admin Login Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response after a successful administrator login, containing a session token.

```json
{
  "success": true,
  "token": "admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456",
  "username": "admin"
}
```

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

### Add New Token Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response upon successfully adding a new token, confirming success and providing basic details of the added token.

```json
{
  "success": true,
  "message": "Token添加成功",
  "token": {
    "id": 2,
    "email": "newuser@example.com",
    "credits": 1000,
    "project_id": "new-project-uuid",
    "project_name": "我的项目"
  }
}
```

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

### Refresh Token Balance Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response after successfully refreshing a token's balance, showing the new credit amount.

```json
{
  "success": true,
  "message": "余额刷新成功",
  "credits": 850
}
```

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

### ST to AT Conversion Tool Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response from the ST to AT conversion tool, showing success, the converted access token, and its expiration.

```json
{
  "success": true,
  "message": "ST converted to AT successfully",
  "access_token": "ya29.a0ARrdaM...",
  "email": "user@example.com",
  "expires": "2025-01-15T04:46:04.000Z"
}
```

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

### Deploy Locally

Source: https://github.com/xiaomo-123/flow2api/blob/main/README.md

Steps to set up a local Python environment and start the service manually.

```bash
# 克隆项目
git clone https://github.com/TheSmallHanCat/flow2api.git
cd sora2api

# 创建虚拟环境
python -m venv venv

# 激活虚拟环境
# Windows
venv\Scripts\activate
# Linux/Mac
source venv/bin/activate

# 安装依赖
pip install -r requirements.txt

# 启动服务
python main.py
```

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

### Batch Import Tokens Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response after a batch token import, indicating success and summarizing the number of tokens added and updated.

```json
{
  "success": true,
  "message": "导入完成",
  "added": 2,
  "updated": 0,
  "errors": []
}
```

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

### Refresh Access Token Response Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example JSON response after successfully refreshing an Access Token, confirming the action and providing the new expiration time.

```json
{
  "success": true,
  "message": "AT刷新成功",
  "token": {
    "id": 1,
    "email": "user@example.com",
    "at_expires": "2025-01-16T04:46:04.000Z"
  }
}
```

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

### Deploy with Docker

Source: https://github.com/xiaomo-123/flow2api/blob/main/README.md

Commands to start the service using Docker Compose, either in standard mode or with a WARP proxy.

```bash
# 克隆项目
git clone https://github.com/TheSmallHanCat/flow2api.git
cd flow2api

# 启动服务
docker-compose up -d

# 查看日志
docker-compose logs -f
```

```bash
# 使用 WARP 代理启动
docker-compose -f docker-compose.warp.yml up -d

# 查看日志
docker-compose -f docker-compose.warp.yml logs -f
```

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

### Docker Compose File Example

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example docker-compose.yml configuration for Flow2API. This defines the service, build context, port mappings, volume mounts, environment variables, and restart policy.

```yaml
version: '3.8'
services:
  flow2api:
    build: .
    ports:
      - "8000:8000"
    volumes:
      - ./config:/app/config
      - ./data:/app/data
    environment:
      - TZ=Asia/Shanghai
    restart: unless-stopped
```

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

### GET /v1/models

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve a list of all supported image and video generation models.

```APIDOC
## GET /v1/models

### Description
Retrieves all supported image and video generation models in OpenAI format.

### Method
GET

### Endpoint
/v1/models

### Response
#### Success Response (200)
- **object** (string) - The type of the object, which is 'list'.
- **data** (array) - List of model objects.

#### Response Example
{
  "object": "list",
  "data": [
    {
      "id": "gemini-2.5-flash-image-landscape",
      "object": "model",
      "owned_by": "flow2api",
      "description": "Image generation - GEM_PIX"
    }
  ]
}
```

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

### Setting.toml Configuration File

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Example configuration for the setting.toml file. This file contains global settings, API keys, server configurations, proxy settings, generation timeouts, cache settings, and token refresh intervals.

```toml
[global]
api_key = "your_api_key"        # 外部调用API使用的密钥
admin_username = "admin"         # 管理后台用户名
admin_password = "your_password" # 管理后台密码

[flow]
labs_base_url = "https://labs.google/fx/api"
api_base_url = "https://aisandbox-pa.googleapis.com/v1"
timeout = 120                    # 请求超时时间(秒)
poll_interval = 3.0              # 视频状态轮询间隔(秒)
max_poll_attempts = 200          # 最大轮询次数

[server]
host = "0.0.0.0"
port = 8000

[proxy]
proxy_enabled = false            # 是否启用代理
proxy_url = "socks5://127.0.0.1:1080"  # 代理地址

[generation]
image_timeout = 300              # 图片生成超时(秒)
video_timeout = 1500             # 视频生成超时(秒)

[admin]
error_ban_threshold = 3          # 连续错误N次后自动禁用Token

[cache]
enabled = false                  # 是否启用缓存
timeout = 7200                   # 缓存超时(秒)
base_url = ""                    # 缓存文件访问URL

[token_refresh]
interval = 3600                  # Token自动刷新间隔(秒)
```

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

### Get Available Models List

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve a list of all supported image and video generation models in OpenAI format. Requires authentication.

```bash
curl -X GET "http://localhost:8000/v1/models" \
  -H "Authorization: Bearer han1234"
```

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

### Get Generation Timeout Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve the configured timeouts for image and video generation.

```bash
curl -X GET "http://localhost:8000/api/config/generation" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Generate Video from Start and End Frames

Source: https://github.com/xiaomo-123/flow2api/blob/main/README.md

API request to generate a video transition between two provided images.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3_1_i2v_s_fast_fl_landscape",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "从第一张图过渡到第二张图"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,<首帧base64>"
            }
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,<尾帧base64>"
            }
          }
        ]
      }
    ],
    "stream": true
  }'
```

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

### Get Proxy Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Use this endpoint to retrieve the current proxy configuration settings.

```bash
curl -X GET "http://localhost:8000/api/proxy/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Docker Compose Standard Deployment

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Instructions for deploying Flow2API using Docker Compose in standard mode without a proxy. Includes cloning the repository, starting the service, viewing logs, and stopping the service.

```bash
# 克隆项目
git clone https://github.com/TheSmallHanCat/flow2api.git
cd flow2api

# 启动服务
docker-compose up -d

# 查看日志
docker-compose logs -f

# 停止服务
docker-compose down
```

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

### Get All Tokens API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve detailed information for all tokens in the system, including balance and usage statistics. Requires an Authorization header with the admin token.

```bash
curl -X GET "http://localhost:8000/api/tokens" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### GET /api/tokens

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieves a list of all tokens in the system along with their usage statistics and configuration.

```APIDOC
## GET /api/tokens

### Description
Fetches detailed information for all tokens, including credits and concurrency limits.

### Method
GET

### Endpoint
http://localhost:8000/api/tokens
```

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

### Get System Statistics

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve overall system statistics, including token counts, generation statistics, and error counts.

```bash
curl -X GET "http://localhost:8000/api/stats" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Proxy Configuration API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

APIs to get and update the proxy configuration for the service.

```APIDOC
## GET /api/proxy/config

### Description
Retrieves the current proxy configuration.

### Method
GET

### Endpoint
/api/proxy/config

### Request Example
```bash
curl -X GET "http://localhost:8000/api/proxy/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

### Response
#### Success Response (200)
- **proxy_enabled** (boolean) - Indicates if the proxy is enabled.
- **proxy_url** (string) - The URL of the proxy server.

#### Response Example
```json
{
  "proxy_enabled": true,
  "proxy_url": "socks5://127.0.0.1:1080"
}
```

## POST /api/proxy/config

### Description
Updates the proxy configuration.

### Method
POST

### Endpoint
/api/proxy/config

### Request Body
- **proxy_enabled** (boolean) - Required - Whether to enable the proxy.
- **proxy_url** (string) - Required - The URL of the proxy server.

### Request Example
```json
{
  "proxy_enabled": true,
  "proxy_url": "socks5://127.0.0.1:1080"
}
```

### Response
#### Success Response (200)
- **message** (string) - Confirmation message.

#### Response Example
```json
{
  "message": "Proxy configuration updated successfully."
}
```
```

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

### Get Token Refresh Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve the configuration for the automatic Access Token refresh feature.

```bash
curl -X GET "http://localhost:8000/api/token-refresh/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Get Cache Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve the current configuration for the local cache, including its enabled status, timeout, and base URL.

```bash
curl -X GET "http://localhost:8000/api/cache/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Cache Configuration API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

APIs to get and update the cache configuration for generation results.

```APIDOC
## GET /api/cache/config

### Description
Retrieves the current cache configuration.

### Method
GET

### Endpoint
/api/cache/config

### Request Example
```bash
curl -X GET "http://localhost:8000/api/cache/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

### Response
#### Success Response (200)
- **enabled** (boolean) - Whether cache is enabled.
- **timeout** (integer) - Cache timeout in seconds.
- **base_url** (string) - The base URL for accessing cached files.

#### Response Example
```json
{
  "enabled": true,
  "timeout": 7200,
  "base_url": "https://your-domain.com"
}
```

## POST /api/cache/config

### Description
Updates the cache configuration.

### Method
POST

### Endpoint
/api/cache/config

### Request Body
- **enabled** (boolean) - Required - Whether to enable cache.
- **timeout** (integer) - Required - Cache timeout in seconds.
- **base_url** (string) - Required - The base URL for accessing cached files.

### Request Example
```json
{
  "enabled": true,
  "timeout": 7200,
  "base_url": "https://your-domain.com"
}
```

### Response
#### Success Response (200)
- **message** (string) - Confirmation message.

#### Response Example
```json
{
  "message": "Cache configuration updated successfully."
}
```
```

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

### Generation Timeout Configuration API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

APIs to get and update the image and video generation timeout settings.

```APIDOC
## GET /api/config/generation

### Description
Retrieves the current generation timeout configuration for images and videos.

### Method
GET

### Endpoint
/api/config/generation

### Request Example
```bash
curl -X GET "http://localhost:8000/api/config/generation" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

### Response
#### Success Response (200)
- **image_timeout** (integer) - Timeout for image generation in seconds.
- **video_timeout** (integer) - Timeout for video generation in seconds.

#### Response Example
```json
{
  "image_timeout": 300,
  "video_timeout": 1500
}
```

## POST /api/config/generation

### Description
Updates the image and video generation timeout settings.

### Method
POST

### Endpoint
/api/config/generation

### Request Body
- **image_timeout** (integer) - Required - Timeout for image generation in seconds.
- **video_timeout** (integer) - Required - Timeout for video generation in seconds.

### Request Example
```json
{
  "image_timeout": 300,
  "video_timeout": 1500
}
```

### Response
#### Success Response (200)
- **message** (string) - Confirmation message.

#### Response Example
```json
{
  "message": "Generation timeout configuration updated successfully."
}
```
```

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

### Token Refresh Configuration API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

APIs to get and update the Access Token auto-refresh configuration.

```APIDOC
## GET /api/token-refresh/config

### Description
Retrieves the current Access Token auto-refresh configuration.

### Method
GET

### Endpoint
/api/token-refresh/config

### Request Example
```bash
curl -X GET "http://localhost:8000/api/token-refresh/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

### Response
#### Success Response (200)
- **interval** (integer) - The interval in seconds for token refresh.

#### Response Example
```json
{
  "interval": 3600
}
```

## POST /api/token-refresh/enabled

### Description
Enables or disables the Access Token auto-refresh feature.

### Method
POST

### Endpoint
/api/token-refresh/enabled

### Request Body
- **enabled** (boolean) - Required - Whether to enable or disable auto-refresh.

### Request Example
```json
{
  "enabled": true
}
```

### Response
#### Success Response (200)
- **message** (string) - Confirmation message.

#### Response Example
```json
{
  "message": "Token refresh enabled successfully."
}
```
```

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

### Configuration File Explanation

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Explanation of the `setting.toml` configuration file.

```APIDOC
## Configuration File Explanation

### `setting.toml` Configuration

This is the main configuration file, containing API keys, server settings, and proxy configurations.

```toml
[global]
api_key = "your_api_key"        # API key for external calls
admin_username = "admin"         # Admin backend username
admin_password = "your_password" # Admin backend password

[flow]
labs_base_url = "https://labs.google/fx/api"
api_base_url = "https://aisandbox-pa.googleapis.com/v1"
timeout = 120                    # Request timeout in seconds
poll_interval = 3.0              # Video status polling interval in seconds
max_poll_attempts = 200          # Maximum polling attempts

[server]
host = "0.0.0.0"
port = 8000

[proxy]
proxy_enabled = false            # Whether to enable proxy
proxy_url = "socks5://127.0.0.1:1080"  # Proxy address

[generation]
image_timeout = 300              # Image generation timeout in seconds
video_timeout = 1500             # Video generation timeout in seconds

[admin]
error_ban_threshold = 3          # Auto-ban token after N consecutive errors

[cache]
enabled = false                  # Whether to enable cache
timeout = 7200                   # Cache timeout in seconds
base_url = ""                    # URL for accessing cached files

[token_refresh]
interval = 3600                  # Token auto-refresh interval in seconds
```
```

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

### Generate Video from Reference Images

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Use this endpoint to create a video from multiple reference images. Supports an unlimited number of images. Ensure images are base64 encoded.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3_0_r2v_fast_landscape",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "将这些产品图片制作成一个展示视频"
          },
          {
            "type": "image_url",
            "image_url": {"url": "data:image/jpeg;base64,<图片1>"}
          },
          {
            "type": "image_url",
            "image_url": {"url": "data:image/jpeg;base64,<图片2>"}
          },
          {
            "type": "image_url",
            "image_url": {"url": "data:image/jpeg;base64,<图片3>"}
          }
        ]
      }
    ],
    "stream": true
}'
```

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

### Image-to-Video Generation (First/Last Frame)

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Generate a transitional video using 1-2 images as the first and last frames. Supports streaming output. Ensure the correct model ID is used for landscape or portrait orientation.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3_1_i2v_s_fast_fl_landscape",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "从第一张图平滑过渡到第二张图，展现日出到日落的变化"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,<首帧图片base64>"
            }
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,<尾帧图片base64>"
            }
          }
        ]
      }
    ],
    "stream": true
  }'
```

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

### Docker Deployment

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Instructions for deploying Flow2API using Docker.

```APIDOC
## Docker Deployment

### Standard Mode Deployment

This describes the standard Docker deployment without a proxy.

```bash
# Clone the project
git clone https://github.com/TheSmallHanCat/flow2api.git
cd flow2api

# Start the service
docker-compose up -d

# View logs
docker-compose logs -f

# Stop the service
docker-compose down
```

**docker-compose.yml Configuration:**
```yaml
version: '3.8'
services:
  flow2api:
    build: .
    ports:
      - "8000:8000"
    volumes:
      - ./config:/app/config
      - ./data:/app/data
    environment:
      - TZ=Asia/Shanghai
    restart: unless-stopped
```

### WARP Proxy Mode Deployment

This describes deployment using Cloudflare WARP proxy.

```bash
# Start with WARP proxy
docker-compose -f docker-compose.warp.yml up -d

# View logs
docker-compose -f docker-compose.warp.yml logs -f
```
```

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

### POST /api/tokens/import

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Bulk imports multiple tokens into the system.

```APIDOC
## POST /api/tokens/import

### Description
Imports a list of tokens, automatically handling creation or updates.

### Method
POST

### Endpoint
http://localhost:8000/api/tokens/import

### Request Body
- **tokens** (array) - Required - List of token objects to import
```

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

### POST /v1/chat/completions

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Generates a video from multiple reference images by sending a request to the chat completions endpoint.

```APIDOC
## POST /v1/chat/completions

### Description
Uploads multiple reference images to generate a video based on the provided prompt.

### Method
POST

### Endpoint
http://localhost:8000/v1/chat/completions

### Request Body
- **model** (string) - Required - The model identifier (e.g., "veo_3_0_r2v_fast_landscape")
- **messages** (array) - Required - List of message objects containing text and image_url content
- **stream** (boolean) - Optional - Whether to stream the response
```

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

### Open Token Import Modal

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Opens the modal for importing tokens, clearing the file input.

```javascript
openImportModal=()=>{$('importModal').classList.remove('hidden');$('importFile').value=''}
```

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

### POST /v1/chat/completions

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Unified endpoint for text-to-image, image-to-image, text-to-video, and image-to-video generation tasks.

```APIDOC
## POST /v1/chat/completions

### Description
Generates content based on the specified model and input messages. Supports text-to-image, image-to-image, text-to-video, and image-to-video generation.

### Method
POST

### Endpoint
/v1/chat/completions

### Request Body
- **model** (string) - Required - The ID of the model to use.
- **messages** (array) - Required - The input messages containing text or image_url content.
- **stream** (boolean) - Optional - Whether to stream the response.

### Request Example
{
  "model": "gemini-2.5-flash-image-landscape",
  "messages": [
    {
      "role": "user",
      "content": "一只可爱的猫咪在花园里玩耍"
    }
  ],
  "stream": true
}
```

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

### Get Request Logs

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Retrieve recent API request logs for debugging and monitoring purposes. You can specify a limit for the number of logs returned.

```bash
curl -X GET "http://localhost:8000/api/logs?limit=50" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Generate Video from Text

Source: https://github.com/xiaomo-123/flow2api/blob/main/README.md

API request to generate a video from a text prompt.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3_1_t2v_fast_landscape",
    "messages": [
      {
        "role": "user",
        "content": "一只小猫在草地上追逐蝴蝶"
      }
    ],
    "stream": true
  }'
```

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

### POST /api/tokens

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Adds a new session token to the system and initializes its associated account information.

```APIDOC
## POST /api/tokens

### Description
Registers a new session token and converts it to an access token.

### Method
POST

### Endpoint
http://localhost:8000/api/tokens

### Request Body
- **st** (string) - Required - Session token string
- **project_name** (string) - Required - Name of the project
- **remark** (string) - Optional - Description of the token
- **image_enabled** (boolean) - Optional - Enable image generation
- **video_enabled** (boolean) - Optional - Enable video generation
- **image_concurrency** (integer) - Optional - Image concurrency limit
- **video_concurrency** (integer) - Optional - Video concurrency limit
```

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

### Batch Import Tokens API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Import multiple tokens in bulk. The system will automatically handle new additions and updates. Requires admin authorization.

```bash
curl -X POST "http://localhost:8000/api/tokens/import" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456" \
  -H "Content-Type: application/json" \
  -d '{
    "tokens": [
      {
        "session_token": "st_token_1",
        "project_name": "项目1",
        "remark": "账号1",
        "image_enabled": true,
        "video_enabled": true
      },
      {
        "session_token": "st_token_2",
        "project_name": "项目2",
        "remark": "账号2",
        "image_enabled": true,
        "video_enabled": false
      }
    ]
  }'
```

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

### Token Data Formatting Utilities

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Helper functions to format token expiry, plan types, and account status for display in the UI.

```javascript
formatExpiry=exp=>{if(!exp)return'<span class="text-muted-foreground">-</span>';const d=new Date(exp),now=new Date(),diff=d-now;const dateStr=d.toLocaleDateString('zh-CN',{year:'numeric',month:'2-digit',day:'2-digit'}).replace(/\//g,'-');const timeStr=d.toLocaleTimeString('zh-CN',{hour:'2-digit',minute:'2-digit',hour12:false});const hours=Math.floor(diff/36e5);if(diff<0)return`<span class="text-red-600 font-medium" title="已过期">已过期</span>`;if(hours<1)return`<span class="text-red-600 font-medium" title="${dateStr} ${timeStr}">${Math.floor(diff/6e4)}分钟</span>`;if(hours<24)return`<span class="text-orange-600 font-medium" title="${dateStr} ${timeStr}">${hours}小时</span>`;const days=Math.floor(diff/864e5);if(days<7)return`<span class="text-orange-600" title="${dateStr} ${timeStr}">${days}天</span>`;return`<span class="text-muted-foreground" title="${dateStr} ${timeStr}">${days}天</span>`}, formatPlanType=type=>{if(!type)return'-';const typeMap={'chatgpt_team':'Team','chatgpt_plus':'Plus','chatgpt_pro':'Pro','chatgpt_free':'Free'};return typeMap[type]||type}, formatSora2=(t)=>{if(t.sora2_supported===true){const remaining=t.sora2_total_count-t.sora2_redeemed_count;const tooltipText=`邀请码: ${t.sora2_invite_code||'无'}\n可用次数: ${remaining}/${t.sora2_total_count}\n已用次数: ${t.sora2_redeemed_count}`;return`<div class="inline-flex items-center gap-1"><span class="inline-flex items-center rounded px-2 py-0.5 text-xs bg-green-50 text-green-700 cursor-pointer" title="${tooltipText}" onclick="copySora2Code('${t.sora2_invite_code||''}')">支持</span><span class="text-xs text-muted-foreground" title="${tooltipText}">${remaining}/${t.sora2_total_count}</span></div>`}else if(t.sora2_supported===false){return`<span class="inline-flex items-center rounded px-2 py-0.5 text-xs bg-gray-100 text-gray-700 cursor-pointer" title="点击使用邀请码激活" onclick="openSora2Modal(${t.id})">不支持</span>`}else{return'-'}}, formatPlanTypeWithTooltip=(t)=>{const tooltipText=t.subscription_end?`套餐到期: ${new Date(t.subscription_end).toLocaleDateString('zh-CN',{year:'numeric',month:'2-digit',day:'2-digit'}).replace(/\//g,'-')} ${new Date(t.subscription_end).toLocaleTimeString('zh-CN',{hour:'2-digit',minute:'2-digit',hour12:false})}`:'';return`<span class="inline-flex items-center rounded px-2 py-0.5 text-xs bg-blue-50 text-blue-700 cursor-pointer" title="${tooltipText||t.plan_title||'-'}">${formatPlanType(t.plan_type)}</span>`}, formatSora2Remaining=(t)=>{if(t.sora2_supported===true){const remaining=t.sora2_remaining_count||0;return`<span class="text-xs">${remaining}</span>`}else{return'-'}}, formatAccountType=(tier)=>{if(tier==='PAYGATE_TIER_NOT_PAID'){return`<span class="inline-flex items-center rounded px-2 py-0.5 text-xs bg-gray-100 text-gray-700">普通</span>`}else{return`<span class="inline-flex items-center rounded px-2 py-0.5 text-xs bg-purple-50 text-purple-700">会员</span>`}}
```

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

### Update Generation Timeout Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Update the timeout settings for image and video generation. Specify timeouts in seconds.

```bash
curl -X POST "http://localhost:8000/api/config/generation" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456" \
  -H "Content-Type: application/json" \
  -d '{
    "image_timeout": 300,
    "video_timeout": 1500
  }'
```

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

### Load System Logs

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Fetches the most recent system logs from the API.

```javascript
loadLogs=async()=>{try{const r=await apiRequest('/api/logs?limit=100');if(!r)return;const logs
```

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

### Image-to-Image Transformation

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Transform an input image based on a text prompt using Imagen models. The image can be provided as a base64 encoded string. Supports streaming output.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "imagen-4.0-generate-preview-landscape",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "将这张图片变成水彩画风格"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
            }
          }
        ]
      }
    ],
    "stream": true
  }'
```

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

### POST /api/admin/login

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Authenticates an administrator and returns a session token for subsequent API requests.

```APIDOC
## POST /api/admin/login

### Description
Logs in the administrator to obtain a session token.

### Method
POST

### Endpoint
http://localhost:8000/api/admin/login

### Request Body
- **username** (string) - Required - Admin username
- **password** (string) - Required - Admin password

### Response
#### Success Response (200)
- **success** (boolean) - Status of the login
- **token** (string) - Authentication token
- **username** (string) - Authenticated username
```

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

### Text-to-Video Generation

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Generate video from text prompts using Veo models. Does not support image uploads. Supports streaming output. Ensure the correct model ID is used for landscape or portrait orientation.

```bash
curl -X POST "http://localhost:8000/v1/chat/completions" \
  -H "Authorization: Bearer han1234" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo_3_1_t2v_fast_landscape",
    "messages": [
      {
        "role": "user",
        "content": "一只小猫在草地上追逐蝴蝶，阳光明媚"
      }
    ],
    "stream": true
  }'
```

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

### Admin Login API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Log in to the admin backend to obtain a session token for subsequent management operations. Requires username and password.

```bash
curl -X POST "http://localhost:8000/api/admin/login" \
  -H "Content-Type: application/json" \
  -d '{
    "username": "admin",
    "password": "admin"
  }'
```

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

### Update Proxy Configuration

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Use this endpoint to update the proxy configuration, enabling or disabling the proxy and setting its URL.

```bash
curl -X POST "http://localhost:8000/api/proxy/config" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456" \
  -H "Content-Type: application/json" \
  -d '{
    "proxy_enabled": true,
    "proxy_url": "socks5://127.0.0.1:1080"
  }'
```

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

### Manage Token Refresh Configuration

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Functions to toggle and load the automatic token refresh status.

```javascript
toggleATAutoRefresh=async()=>{try{const enabled=$('atAutoRefreshToggle').checked;console.log("自动刷新"); const r=await apiRequest('/api/token-refresh/enabled',{method:'POST',body:JSON.stringify({enabled:enabled})});if(!r){$('atAutoRefreshToggle').checked=!enabled;return}const d=await r.json();if(d.success){showToast(enabled?'AT自动刷新已启用':'AT自动刷新已禁用','success')}else{showToast('操作失败: '+(d.detail||'未知错误'),'error');$('atAutoRefreshToggle').checked=!enabled}}catch(e){showToast('操作失败: '+e.message,'error');$('atAutoRefreshToggle').checked=!enabled}}
```

```javascript
loadATAutoRefreshConfig=async()=>{try{const r=await apiRequest('/api/token-refresh/config');if(!r)return;const d=await r.json();if(d.success&&d.config){$('atAutoRefreshToggle').checked=d.config.at\_auto\_refresh\_enabled||false}else{console.error('AT自动刷新配置数据格式错误:',d)}}catch(e){console.error('加载AT自动刷新配置失败:',e)}}
```

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

### Add New Token API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Add a new Session Token to the system. It will be automatically converted to an Access Token, and account information will be retrieved. Requires admin authorization.

```bash
curl -X POST "http://localhost:8000/api/tokens" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456" \
  -H "Content-Type: application/json" \
  -d '{
    "st": "__Secure-next-auth.session-token=eyJhbGciOiJkaXIi...",
    "project_name": "我的项目",
    "remark": "测试账号",
    "image_enabled": true,
    "video_enabled": true,
    "image_concurrency": 3,
    "video_concurrency": 1
  }'
```

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

### Token Management and API Utilities

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Core functions for handling authentication, API requests, and loading system statistics and token data.

```javascript
let allTokens=[]; const $=(id)=>document.getElementById(id), checkAuth=()=>{const t=localStorage.getItem('adminToken');return t||(location.href='/login',null),t}, apiRequest=async(url,opts={})=>{const t=checkAuth();if(!t)return null;const r=await fetch(url,{...opts,headers:{...opts.headers,Authorization:`Bearer ${t}`,'Content-Type':'application/json'}});return r.status===401?(localStorage.removeItem('adminToken'),location.href='/login',null):r}, loadStats=async()=>{try{const r=await apiRequest('/api/stats');if(!r)return;const d=await r.json();$('statTotal').textContent=d.total_tokens||0;$('statActive').textContent=d.active_tokens||0;$('statImages').textContent=(d.today_images||0)+'/'+(d.total_images||0);$('statVideos').textContent=(d.today_videos||0)+'/'+(d.total_videos||0);$('statErrors').textContent=(d.today_errors||0)+'/'+(d.total_errors||0)}catch(e){console.error('加载统计失败:',e)}}, loadTokens=async()=>{try{const r=await apiRequest('/api/tokens');if(!r)return;allTokens=await r.json();renderTokens()}catch(e){console.error('加载Token失败:',e)}}
```

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

### Proxy and Debug Configuration

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Functions to toggle debug mode and manage proxy settings.

```javascript
toggleDebugMode=async()=>{const enabled=$('cfgDebugEnabled').checked;try{const r=await apiRequest('/api/admin/debug',{method:'POST',body:JSON.stringify({enabled:enabled})});if(!r)return;const d=await r.json();if(d.success){showToast(enabled?'调试模式已开启':'调试模式已关闭','success')}else{showToast('操作失败: '+(d.detail||'未知错误'),'error');$('cfgDebugEnabled').checked=!enabled}}catch(e){showToast('操作失败: '+e.message,'error');$('cfgDebugEnabled').checked=!enabled}}
```

```javascript
loadProxyConfig=async()=>{try{const r=await apiRequest('/api/proxy/config');if(!r)return;const d=await r.json();$('cfgProxyEnabled').checked=d.proxy_enabled||false;$('cfgProxyUrl').value=d.proxy_url||''}catch(e){console.error('加载代理配置失败:',e)}}
```

```javascript
saveProxyConfig=async()=>{try{const r=await apiRequest('/api/proxy/config',{method:'POST',body:JSON.stringify({proxy_enabled:$('cfgProxyEnabled').checked,proxy_url:$('cfgProxyUrl').value.trim()})});if(!r)return;const d=await r.json();d.success?showToast('代理配置保存成功','success'):showToast('保存失败','error')}catch(e){showToast('保存失败: '+e.message,'error')}}
```

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

### Batch Token Management

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Functions for refreshing multiple tokens and managing UI selection states.

```javascript
refreshTokens=async()=>{ // 打印选中的Token ID const selectedCheckboxes = document.querySelectorAll('.token-checkbox:checked'); const selectedIds = Array.from(selectedCheckboxes).map(cb => cb.value); if (selectedIds.length > 0) { console.log("选中的Token ID:", selectedIds.join(", ")); await batchRefreshTokens(selectedIds); } // 原有的刷新功能 console.log("刷新"); loadTokens(); await loadStats(); }, // 批量刷新Token的AT batchRefreshTokens=async(tokenIds)=>{ showToast(`正在刷新 ${tokenIds.length} 个Token的AT...`, 'info'); let successCount = 0; let failCount = 0; for (const id of tokenIds) { try { const r = await apiRequest(`/api/tokens/${id}/refresh-at`, {method: 'POST'}); if (!r) { failCount++; continue; } const d = await r.json(); if (d.success) { successCount++; console.log(`Token ${id} AT刷新成功`); } else { failCount++; console.error(`Token ${id} AT刷新失败:`, d.detail || '未知错误'); } } catch (e) { failCount++; console.error(`Token ${id} AT刷新异常:`, e.message); } } if (successCount > 0) { showToast(`AT刷新完成: 成功 ${successCount} 个, 失败 ${failCount} 个`, 'success'); } else { showToast(`AT刷新失败: 所有 ${failCount} 个Token刷新失败`, 'error'); } }, // 全选/取消全选功能 toggleSelectAll=()=>{ const selectAllCheckbox = $('selectAllTokens'); const tokenCheckboxes = document.querySelectorAll('.token-checkbox'); tokenCheckboxes.forEach(checkbox => { checkbox.checked = selectAllCheckbox.checked; }); }, // 更新全选框状态 updateSelectAllStatus=()=>{ const selectAllCheckbox = $('selectAllTokens'); const tokenCheckboxes = document.querySelectorAll('.token-checkbox'); const checkedCheckboxes = document.querySelectorAll('.token-checkbox:checked'); // 如果没有Token，不更新全选框状态 if (tokenCheckboxes.length === 0) { return; } // 如果所有Token都被选中，则全选框也选中 // 如果有Token未被选中，则全选框不选中 selectAllCheckbox.checked = tokenCheckboxes.length === checkedCheckboxes.length; }, openAddModal=()=>$('addModal').classList.remove('hidden'), closeAddModal=()=>{$('addModal').classList.add('hidden')}
```

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

### Refresh Token Balance API

Source: https://context7.com/xiaomo-123/flow2api/llms.txt

Manually refresh the VideoFX Credits balance for a specific token. Requires admin authorization and the token ID.

```bash
curl -X POST "http://localhost:8000/api/tokens/1/refresh-credits" \
  -H "Authorization: Bearer admin-aBcDeFgHiJkLmNoPqRsTuVwXyZ123456"
```

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

### Export All Tokens

Source: https://github.com/xiaomo-123/flow2api/blob/main/static/manage.html

Exports all current tokens to a JSON file. The export includes token details like email, access token, session token, and various flags and concurrency settings.

```javascript
exportTokens=()=>{if(allTokens.length===0){showToast('没有Token可导出','error');return}const exportData=allTokens.map(t=>({email:t.email,access_token:t.token,session_token:t.st||null,is_active:t.is_active,image_enabled:t.image_enabled!==false,video_enabled:t.video_enabled!==false,image_concurrency:t.image_concurrency||(-1),video_concurrency:t.video_concurrency||(-1)}));const dataStr=JSON.stringify(exportData,null,2);const dataBlob=new Blob([dataStr],{type:'application/json'});const url=URL.createObjectURL(dataBlob);const link=document.createElement('a');link.href=url;link.download=`tokens_${new Date().toISOString().split('T')[0]}.json`;document.body.appendChild(link);link.click();document.body.removeChild(link);URL.revokeObjectURL(url);showToast(`已导出 ${allTokens.length} 个Token`,'success')}
```