### Start OpenClaw Onboarding

Source: https://www.tokenrouter.com/docs/openclaw-setup

Starts the OpenClaw onboarding wizard and installs the OpenClaw Gateway as a background service.

```bash
openclaw onboard --install-daemon

```

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

### Get Account Wallet - Response Example

Source: https://www.tokenrouter.com/docs/management-api-documentation

Example JSON response for the Get Account Wallet endpoint, showing top-up and voucher balances.

```json
{
  "success": true,
  "message": "",
  "data": {
    "topUpBalance": 120.50,
    "voucherEfficientAmount": 30.00,
    "toppedUpSpent": 80.25,
    "voucherSpent": 10.00
  }
}
```

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

### Start OpenClaw Onboarding

Source: https://www.tokenrouter.com/docs/openclaw-setup

Run this command to start the onboarding wizard and install the OpenClaw Gateway as a background service.

```bash
openclaw onboard --install-daemon
```

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

### Install TokenRouter on macOS/Linux with curl

Source: https://www.tokenrouter.com/docs/setup-tokenrouter-in-codex-chatgpt

Run this command in Terminal. Replace <YOUR_API_KEY> with your own API key before executing. Installs Codex/ChatGPT normally after setup.

```bash
curl -fsSL https://raw.githubusercontent.com/TokenRouter-Tools/codex-inject/main/install.sh | bash -s -- <YOUR_API_KEY>
```

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

### Install TokenRouter on Windows with PowerShell

Source: https://www.tokenrouter.com/docs/setup-tokenrouter-in-codex-chatgpt

Run this command in Windows PowerShell. Replace <YOUR_API_KEY> with your own API key before executing. Installs Codex/ChatGPT normally after setup.

```powershell
irm https://raw.githubusercontent.com/TokenRouter-Tools/codex-inject/main/install.ps1 | iex; install <YOUR_API_KEY>
```

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

### Install OpenClaw with npm

Source: https://www.tokenrouter.com/docs/openclaw-setup

Alternative installation method using npm. Use only if you already manage Node.js.

```bash
npm install -g openclaw@latest
```

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

### Install OpenClaw with npm

Source: https://www.tokenrouter.com/docs/openclaw-setup

Alternative installation method using npm. Use only when you already manage Node.js on your computer.

```bash
npm install -g openclaw@latest

```

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

### Send a test message to Claude Code

Source: https://www.tokenrouter.com/docs/claude-code-setup

Send a simple message to Claude Code to verify the setup. The example asks for a project directory structure overview.

```plaintext
请介绍一下这个项目的目录结构。

```

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

### List API Keys (GET /api/management/api-keys) - curl example

Source: https://www.tokenrouter.com/docs/management-api-documentation

Returns a paginated list of API keys for the current account. Use page and page_size query parameters. Responses mask key values and do not expose internal IDs.

```bash
curl -s "$BASE_URL/api/management/api-keys?page=1&page_size=10" \
  -H "Authorization: Bearer $MGMT_KEY"

```

```json
{
  "success": true,
  "message": "",
  "data": {
    "page": 1,
    "page_size": 10,
    "total": 2,
    "items": [
      {
        "name": "my-app-key",
        "key": "sk-abcd**********wxyz",
        "status": 1,
        "status_tips": "status: 1->enable 2->disable",
        "unlimited_quota": false,
        "unlimited_tips": "unlimited_quota: true->No-Limit false->Limit by remain_quota",
        "remain_quota": 10.0,
        "used_quota": 2.5,
        "expired_time": -1,
        "expired_time_tips": "expired_time: -1->Never-Expires 1xxxxxxxx->Expiry date UTC timestamp",
        "created_time": 1716200000
      }
    ]
  }
}

```

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

### Text to Image Generation Examples

Source: https://www.tokenrouter.com/docs/how-to-use-image-models

Examples for text-to-image generation using the OpenAI-compatible endpoint.

```http
POST /v1/images/generations

```

```bash
curl -X POST https://api.tokenrouter.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5-image",
    "prompt": "Draw an orange cat playing guitar on the moon.",
    "n": 2,
    "size": "1024x1024",
    "quality": "high",
    "background": "transparent"
  }'

```

```python
import requests

API_BASE = "https://api.tokenrouter.com"
API_KEY = "sk-*******************************"

HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

def images_generate():
    data = {
        "model": "openai/gpt-5-image",
        "prompt": "Draw an orange cat playing guitar on the moon.",
        "n": 1,
        "size": "1024x1024",
        "quality": "high"
    }

    try:
        response = requests.post(f'{API_BASE}/v1/images/generations', headers=HEADERS, json=data)
        response.raise_for_status()
        result = response.json()

        print("Generated image URL:", result["data"][0]["url"])

    except Exception as e:
        print("Error:", str(e))

```

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

### Verify OpenClaw Installation

Source: https://www.tokenrouter.com/docs/openclaw-setup

Verifies that OpenClaw was installed successfully by printing the installed version.

```bash
openclaw --version

```

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

### Install OpenClaw on macOS, Linux, or WSL2

Source: https://www.tokenrouter.com/docs/openclaw-setup

Run this command in Terminal to install OpenClaw using the official installer script.

```bash
curl -fsSL https://openclaw.ai/install.sh | bash
```

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

### Authentication Response Example

Source: https://www.tokenrouter.com/docs/management-api-documentation

Example JSON response from an authentication or API key listing endpoint, showing user data with API keys and quota fields.

```json
{
  "success": true,
  "message": "",
  "data": [
    {
      "email": "alice@example.com",
      "api_keys": [
        {
          "name": "alice-key",
          "key": "sk-1234**********6789",
          "status": 1,
          "status_tips": "status: 1->enable 2->disable",
          "unlimited_quota": true,
          "unlimited_tips": "unlimited_quota: true->No-Limit false->Limit by remain_quota",
          "remain_quota": 0.0,
          "used_quota": 12.34,
          "expired_time": -1,
          "expired_time_tips": "expired_time: -1->Never-Expires 1xxxxxxxx->Expiry date UTC timestamp",
          "created_time": 1716200000
        }
      ]
    },
    {
      "email": "bob@example.com",
      "api_keys": []
    }
  ]
}
```

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

### Verify OpenClaw Installation

Source: https://www.tokenrouter.com/docs/openclaw-setup

Check that OpenClaw was installed successfully by displaying its version.

```bash
openclaw --version
```

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

### Install Claude Code CLI via WinGet

Source: https://www.tokenrouter.com/docs/claude-code-setup

Alternative installation method for Windows when the official default installer fails. Versions installed via WinGet usually require manual updates.

```powershell
winget install --id Anthropic.ClaudeCode -e

```

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

### Install OpenClaw on macOS/Linux/WSL2

Source: https://www.tokenrouter.com/docs/openclaw-setup

Installs OpenClaw on macOS, Linux, or WSL2 using the official installer script. The installer detects the OS, installs dependencies, and installs the latest OpenClaw CLI.

```bash
curl -fsSL https://openclaw.ai/install.sh | bash

```

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

### Hailuo Text to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task using the MiniMax-Hailuo-2.3 model. The response contains a task_id to poll for completion.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "MiniMax-Hailuo-2.3",
    "prompt": "A white fox running across a snowy field, cinematic motion and soft lighting",
    "duration": 6,
    "size": "768P"
  }'
```

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

### Install Claude Code on macOS, Linux, or WSL

Source: https://www.tokenrouter.com/docs/claude-code-setup

Run the official installation script in your terminal.

```bash
curl -fsSL https://claude.ai/install.sh | bash
```

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

### Hailuo Image to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task from a source image using the I2V-01 model. The first_frame_image parameter specifies the input image URL.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "I2V-01",
    "prompt": "A subtle blink, gentle head movement, and a slow push-in camera",
    "first_frame_image": "https://example.com/source.png",
    "duration": 6,
    "size": "768P"
  }'
```

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

### Kling Text to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task using the kling-v3 model in pro mode. The metadata includes aspect ratio, sound, and negative prompt.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "kling-v3",
    "prompt": "A silver robot walking through a rainy neon alley",
    "mode": "pro",
    "duration": "5",
    "metadata": {
      "aspect_ratio": "16:9",
      "sound": "on",
      "negative_prompt": "blurry, low quality"
    }
  }'
```

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

### Kling Image to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task from an image using the kling-v2-6 model. The image parameter specifies the input image URL.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "kling-v2-6",
    "prompt": "The girl smiles slightly and the camera slowly pushes in",
    "image": "https://example.com/portrait.png",
    "mode": "pro",
    "duration": "5",
    "metadata": {
      "sound": "off",
      "negative_prompt": "flicker, blur"
    }
  }'
```

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

### Universal Video Model Request Example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

A JSON request body for generating a video with the kling-v3 model. It includes a prompt, metadata with mode, duration, aspect ratio, and sound settings. This example appears twice in the source, once in a code block and once in a numbered list.

```json
{
  "model": "kling-v3",
  "prompt": "A futuristic city street at night, cinematic camera movement",
  "metadata": {
    "mode": "pro",
    "duration": "5",
    "aspect_ratio": "16:9",
    "sound": "on"
  }
}
```

```json
{
  "model": "kling-v3",
  "prompt": "A futuristic city street at night, cinematic camera movement",
  "metadata": {
    "mode": "pro",
    "duration": "5",
    "aspect_ratio": "16:9",
    "sound": "on"
  }
}
```

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

### Query response example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Example JSON response returned when querying a task. The status field shows SUCCESS, and the result_url contains the final video URL. The data object includes details like duration, ratio, resolution, and audio settings.

```json
{
  "code": "success",
  "message": "",
  "data": {
    "id": 17,
    "created_at": 1776323800,
    "updated_at": 1776323943,
    "task_id": "task_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "platform": "45",
    "quota": 500,
    "action": "generate",
    "status": "SUCCESS",
    "result_url": "https://example.com/video.mp4",
    "progress": "100%",
    "properties": {
      "upstream_model_name": "dreamina-seedance-2-0-fast-260128",
      "origin_model_name": "dreamina-seedance-2-0-fast-260128"
    },
    "data": {
      "duration": 5,
      "ratio": "16:9",
      "resolution": "720p",
      "generate_audio": true,
      "status": "succeeded"
    }
  }
}

```

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

### Seedance Multimodal Video Generation with Python

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Python example using the requests library to call the TokenRouter video generation API with the dreamina-seedance-2-0-260128 model. It sends a prompt with image, audio, and video references, and returns the task_id from the response. Requires a valid TokenRouter API key.

```python
import requests

API_BASE = "https://api.tokenrouter.com"
API_KEY = "<YOUR_TOKENROUTER_KEY>"

HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

def seedance_video_all_guide():
    url = f"{API_BASE}/v1/video/generations"
    payload = {
        "model": "dreamina-seedance-2-0-260128",
        "prompt": "Use the first-person POV framing from [Video 1] throughout, and use [Audio 1] as the background music throughout. First-person POV fruit tea promotional ad, seedance limited-edition apple fruit tea; opening frame is [Image 1], your hand picks a dew-covered Aksu red apple, a light, crisp apple tapping sound; 2–4 seconds: fast cuts, your hand drops apple chunks into a shaker, adds ice and tea base, shakes forcefully, ice clinking and shaking sounds sync with upbeat rhythmic beats, background audio: {Fresh-cut, shaken fresh}; 4–6 seconds: first-person close-up of the finished drink, layered fruit tea is poured into a clear cup, your hand gently squeezes milk foam to spread across the top, a pink brand sticker is applied to the cup, the camera moves closer to show the layered textures of the foam and fruit tea; 6–8 seconds: first-person hand-held toast shot, you raise the fruit tea from [Image 2] toward the camera (simulating handing it to the viewer), the cup label is clearly visible, background audio {Take a sip of fresh refreshment}, the final frame freezes on Image 2. All background voice audio uses a female voice.",
        "images": [
            "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic1.jpg",
            "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_image/r2v_tea_pic2.jpg"
        ],
        "audios": [
            "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_audio/r2v_tea_audio1.mp3"
        ],
        "videos": [
            "https://ark-doc.tos-ap-southeast-1.bytepluses.com/doc_video/r2v_tea_video1.mp4"
        ],
        "metadata": {
            "duration": 10,
            "resolution": "1080p"
        }
    }

    try:
        resp = requests.post(url, json=payload, headers=HEADERS, timeout=60)
        resp.raise_for_status()
        data = resp.json()
        return data["task_id"]
    except Exception as e:
        print(f"occur error: {e}")

```

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

### Seedance Text to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task using the doubao-seedance-1-0-lite-t2v model. The metadata includes duration, resolution, ratio, and audio generation.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "doubao-seedance-1-0-lite-t2v",
    "prompt": "A vintage sports car driving along a coastal road at sunset",
    "metadata": {
      "duration": 5,
      "resolution": "1080p",
      "ratio": "16:9",
      "generate_audio": true
    }
  }'
```

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

### Seedance Image to Video curl example

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Creates a video generation task from an image using the doubao-seedance-1-0-lite-i2v model. The images parameter is an array of input image URLs.

```bash
curl -X POST "https://api.tokenrouter.com/v1/video/generations"   -H "Authorization: Bearer YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "doubao-seedance-1-0-lite-i2v",
    "prompt": "The subject looks up toward the camera while hair moves gently in the wind",
    "images": [
      "https://example.com/input-image.png"
    ],
    "metadata": {
      "duration": 5,
      "resolution": "720p",
      "ratio": "9:16"
    }
  }'
```

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

### GET /v1/video/generations/{task_id}

Source: https://www.tokenrouter.com/docs/how-to-use-video-models

Queries the status of a video generation task. Poll every 2 to 5 seconds until the task succeeds, then read the final result_url.

```APIDOC
## GET /v1/video/generations/{task_id}

### Description
Queries the status of a video generation task. Poll every 2 to 5 seconds until the task succeeds, then read the final `result_url`.

### Method
GET

### Endpoint
/v1/video/generations/{task_id}

### Parameters
#### Path Parameters
- **task_id** (string) - Required - The ID of the task to query.

### Response
#### Success Response (200)
- **status** (string) - The status of the task (e.g., pending, processing, succeeded, failed).
- **result_url** (string) - The URL of the generated video, available after the task succeeds.

#### Response Example
```json
{
  "status": "succeeded",
  "result_url": "https://example.com/video.mp4"
}
```
```

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

### Get Member Wallet - Response (200)

Source: https://www.tokenrouter.com/docs/management-api-documentation

Example JSON response for the Get Member Wallet endpoint. Shows quotaTotal, quotaRemaining, and quotaSpent fields.

```json
{
  "success": true,
  "message": "",
  "data": {
    "quotaTotal": 100.00,
    "quotaRemaining": 65.00,
    "quotaSpent": 35.00
  }
}
```

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

### GET /api/management/export/hour/usages

Source: https://www.tokenrouter.com/docs/management-api-documentation

Exports consumption usage logs as a CSV file. Supports optional start and end timestamps to define the query range, which is strictly limited to 1 hour.

```APIDOC
## GET /api/management/export/hour/usages

### Description
Exports consumption usage logs as a CSV file. For enterprise accounts the query covers all members of the organization; for personal accounts it covers only the current user. The query time range is strictly limited to 1 hour (inclusive).

### Method
GET

### Endpoint
/api/management/export/hour/usages

### Parameters
#### Query Parameters
- **start_timestamp** (int) - Optional - Range start (Unix seconds).
- **end_timestamp** (int) - Optional - Range end (Unix seconds).

### Request Example
curl -s "$BASE_URL/api/management/export/hour/usages" \
  -H "Authorization: Bearer $MGMT_KEY" \
  -o usage_logs.csv

### Response
#### Success Response (200)
Returns a CSV file with the following columns: request_id, email, key_name, model_name, prompt_tokens, completion_tokens, cache_creation_tokens, cache_tokens, cost, created_at.

#### Response Example
request_id,email,key_name,model_name,prompt_tokens,completion_tokens,cache_creation_tokens,cache_tokens,cost,created_at
req-abc123,alice@example.com,my-app-key,gpt-4o,1200,340,0,256,0.0124,1716250000
req-def456,bob@example.com,my-app-key,claude-3-5-sonnet,800,210,128,512,0.0089,1716251000

### Errors
Returned as JSON with HTTP 200 before the CSV stream begins.
- `start_timestamp must not be later than end_timestamp` - Cause: `start > end`.
- `time range must not exceed 1 hour` - Cause: Range wider than 1 hour.
```

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

### Callback URL configuration example

Source: https://www.tokenrouter.com/docs/how-to-use-minimax-h3

Example JSON payload showing how to provide a callback_url when creating a task. The URL must be publicly accessible over HTTPS and must return the challenge value unchanged within 3 seconds during verification.

```json
{
  "callback_url": "https://your-domain.example.com/callbacks/minimax-h3"
}
```

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

### List Organization API Keys (GET /api/manage/org/api-keys) - curl example

Source: https://www.tokenrouter.com/docs/management-api-documentation

Lists API keys for the enterprise organization, grouped by member email. Requires the management key owner to belong to an organization.

```bash
curl -s "$BASE_URL/api/management/org/api-keys" \
  -H "Authorization: Bearer $MGMT_KEY"

```