> 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/introduction-to-apismart.md).

# Introduction to ApiSmart

[ApiSmart](https://www.apismart.ai/) is a **unified AI API platform** designed for developers and businesses building AI-powered applications.

Instead of maintaining separate integrations for different AI model providers, ApiSmart provides a centralized way to access supported **text, image, and video models**, manage API credentials, monitor usage, and integrate AI capabilities into your applications.

### 🧩 What Is ApiSmart?

Modern AI applications often rely on multiple models and model providers.

A single application might use one model for conversations or reasoning, another for image generation, and a video model for multimedia workflows. Managing each provider separately can mean working with different credentials, API formats, billing systems, and operational requirements.

ApiSmart simplifies this process by providing a unified API gateway and a consistent developer experience across supported AI services.

With ApiSmart, you can:

* Access multiple AI model families from one platform
* Work with text, image, and video generation APIs
* Use a familiar Chat Completions API format for supported text models
* Switch between supported models with minimal integration changes
* Manage API Keys from a centralized Console
* Monitor API usage and request activity
* Manage usage and billing from one account

### ⚡ Why Use ApiSmart?

#### Unified Model Access

ApiSmart provides a single platform for accessing supported models from different model families.

Instead of maintaining separate provider integrations, your application can use the ApiSmart gateway and select the required model using its `model` ID.

#### Familiar API Integration

Text models use an OpenAI-compatible Chat Completions interface:

`POST /v1/chat/completions`

For applications already built around a Chat Completions-style API, integration typically involves updating the API endpoint, API Key, and model ID rather than redesigning the application architecture.

Image and video models use dedicated endpoints designed for their respective generation workflows.

#### Flexible Model Selection

Each request specifies the model you want to use through the `model` parameter.

For example:

```json
{
  "model": "deepseek-v4-flash"
}
```

You can retrieve the latest available model IDs programmatically:

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

Use the returned `data[].id` value as the `model` parameter in supported API requests.

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

#### Reliability and Observability

ApiSmart is designed to provide a centralized infrastructure layer between your application and supported AI model services.

Platform capabilities include intelligent routing, automatic failover, request monitoring, usage analytics, and centralized cost tracking.

These features help reduce the operational work required to manage multiple independent AI service integrations.

### ✨ Supported AI Workloads

ApiSmart supports multiple types of AI workloads through dedicated APIs.

#### Text Generation

Text models use the Chat Completions API:

`POST /v1/chat/completions`

Common applications include:

* AI assistants
* Conversational interfaces
* Content generation
* Summarization
* Reasoning
* Coding assistance
* Other text-based AI workflows

Text responses can be returned normally or streamed when supported.

#### [Image Generation](/api-guides/image-generation-api.md)

Image generation uses:

`POST /v1/images/generations`

Supported workflows can include:

* Text-to-image generation
* Image-to-image generation
* Multiple reference images
* Sequential image generation
* Image editing
* Streaming image output

Local image uploads can also be handled through:

`POST /v1/images/edits`

#### [Video Generation](/api-guides/video-generation-api.md)

Video generation uses asynchronous tasks:

`POST /v1/video/tasks`

Depending on the selected model, supported workflows can include:

* Text-to-video
* Image-to-video
* Reference-based video generation
* Video editing
* First-frame and last-frame generation
* Multimodal workflows using images, video, and audio

Because video generation is asynchronous, the API returns a task ID that you can use to check generation status.

### 🔑 API Access

The standard ApiSmart API Base URL is:

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

API requests are authenticated using an API Key:

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

You can create and manage API Keys from:

**Console → API Keys**

Keep your API Key secure and never expose it in public repositories, browser-side code, or other publicly accessible locations.

### 🔄 How ApiSmart Works

A typical ApiSmart integration follows four steps:

1. **Create an API Key**\
   Create a credential for your application from the ApiSmart Console.
2. **Choose a Model**\
   Select a supported model or use `GET /v1/models` to retrieve current model IDs.
3. **Send an API Request**\
   Use the appropriate Chat Completions, Image Generation, or Video Generation endpoint.
4. **Monitor Usage**\
   Review API activity, usage, and associated costs from the Console.

This structure allows you to work with different AI capabilities while keeping authentication, model access, usage monitoring, and account management within the same platform.

### 👨‍💻 Who Is ApiSmart For?

ApiSmart is designed for developers and teams that want a simpler way to integrate and manage AI model APIs.

It is suitable for:

* Developers building AI-powered applications
* Teams evaluating multiple AI models
* SaaS products integrating generative AI features
* Backend and platform engineering teams
* Businesses managing multiple AI workloads
* Applications combining text, image, and video generation

Whether you're testing a model for the first time or integrating AI capabilities into a production application, ApiSmart provides a consistent foundation for accessing supported AI services.

### 🚀 Next Steps

If you're new to ApiSmart, continue with:

* [**Quick Start**](/welcome-to-apismart/quick-start.md) — Make your first API request
* [**API Keys**](/welcome-to-apismart/api-keys.md) — Learn how authentication works
* [**Models and Model IDs**](/models-and-pricing/models-and-model-ids.md) — Find and select supported models
* [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md) — Understand how different models are billed
* [**API Basics**](/api-guides/api-basics.md) — Learn the common rules used across ApiSmart APIs

When you're ready to build, explore:

* [**Chat Completions API**](/api-guides/chat-completions-api.md)
* [**Image Generation API**](/api-guides/image-generation-api.md)
* [**Video Generation API**](/api-guides/video-generation-api.md)