> For the complete documentation index, see [llms.txt](https://docs.apismart.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apismart.ai/welcome-to-apismart/quick-start.md).

# Quick Start

Get up and running with ApiSmart in just a few steps.

This guide will show you how to create an API Key, find an available model, and send your first API request.

### 🚀 Before You Start

Make sure you have:

* An ApiSmart account
* Sufficient wallet balance for the model you want to use
* An API Key

If you haven't created an account or added funds yet, see [**Create and Access Your Account**](/account-and-wallet/create-and-access-your-account.md) and [**Add Funds and Understand Wallet Credits**](/account-and-wallet/add-funds-and-understand-wallet-credits.md).

***

### 🔑 Step 1: Create an API Key

Sign in to the ApiSmart Console and go to:

**Console → API Keys**

Click **Create API Key** and create a credential for your application.

Your API Key is used to authenticate API requests.

Throughout this documentation, we use:

`<your-api-key>`

Replace this placeholder with your actual API Key when sending a request.

> Keep your API Key secure. Do not expose it in public repositories, browser-side code, or other publicly accessible locations.

For key management and security best practices, see [**API Keys**](/welcome-to-apismart/api-keys.md).

***

### 🔗 Step 2: Configure the API

The standard ApiSmart API Base URL is:

`https://gw.apismart.ai/v1`

Authenticate requests using the `Authorization` header:

```http
Authorization: Bearer <your-api-key>
```

For JSON requests, also include:

```http
Content-Type: application/json
```

***

### 🧩 Step 3: Find a Model

Before making a request, you can retrieve the current model list:

```bash
curl https://gw.apismart.ai/v1/models \
  -H "Authorization: Bearer <your-api-key>"
```

Example response:

```json
{
  "object": "list",
  "data": [
    {
      "id": "doubao-seedream-5-0",
      "object": "model",
      "owned_by": "api-gateway"
    },
    {
      "id": "deepseek-v4-flash",
      "object": "model",
      "owned_by": "api-gateway"
    }
  ]
}
```

Use the value returned in `data[].id` as the `model` parameter in your API request.

> **Model IDs must match exactly.**\
> Pay attention to periods (`.`), hyphens (`-`), and version numbers.

The Models API may return models that are not enabled for every API Key. If a request returns `403 model_not_allowed`, the selected model is not currently available to your API Key.

For more information, see [**Models and Model IDs**](/models-and-pricing/models-and-model-ids.md).

***

### 💬 Step 4: Send Your First Request

The fastest way to test your integration is with the Chat Completions API.

Send a request to:

`POST /v1/chat/completions`

```bash
curl https://gw.apismart.ai/v1/chat/completions \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello! Please introduce yourself."
      }
    ]
  }'
```

If the request succeeds, the API returns a response generated by the selected model.

You have now completed your first ApiSmart API request.

***

### 🖼️ Optional: Try Image Generation

To generate an image, use:

`POST /v1/images/generations`

Example:

```bash
curl https://gw.apismart.ai/v1/images/generations \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-0",
    "prompt": "A mountain village at sunrise, watercolor style",
    "size": "2K",
    "watermark": false
  }'
```

Image generation is synchronous, so the connection remains open until generation completes.

For longer-running requests, set your client timeout to at least **90 seconds**.

For supported parameters, reference images, image editing, and streaming, see [**Image Generation API**](/api-guides/image-generation-api.md).

***

### 🎬 Optional: Try Video Generation

Video generation uses asynchronous tasks.

Create a task with:

`POST /v1/video/tasks`

```bash
curl https://gw.apismart.ai/v1/video/tasks \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0",
    "prompt": "A miniature city at night with a train moving through the streets",
    "duration": 5,
    "resolution": "720p"
  }'
```

The API returns a task ID.

Use it to check the task status:

```bash
curl https://gw.apismart.ai/v1/video/tasks/<task_id> \
  -H "Authorization: Bearer <your-api-key>"
```

Continue checking until the task reaches a final status such as `succeeded` or `failed`.

> For video requests, explicitly specify parameters such as `resolution` and `duration` when applicable. These values can affect billing.

For model-specific parameters and supported workflows, see [**Video Generation API**](/api-guides/video-generation-api.md).

***

### ✅ You're Ready to Build

You now know how to:

1. Create an API Key
2. Configure the ApiSmart API
3. Retrieve available model IDs
4. Send a Chat Completions request
5. Try image or video generation

Continue with the documentation that matches your workflow:

* [**API Keys**](/welcome-to-apismart/api-keys.md) — Manage and secure your credentials
* [**Models and Model IDs**](/models-and-pricing/models-and-model-ids.md) — Find supported models
* [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md) — Understand model costs
* [**API Basics**](/api-guides/api-basics.md) — Learn common API conventions
* [**Chat Completions API**](/api-guides/chat-completions-api.md) — Build with text models
* [**Image Generation API**](/api-guides/image-generation-api.md) — Generate and edit images
* [**Video Generation API**](/api-guides/video-generation-api.md) — Create video generation workflows
* [**Response Modes**](/api-guides/response-modes.md) — Learn about standard, streaming, and asynchronous responses