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

# What is Uniport AI?

### A Unified Gateway to Multimodal AI

AI development today often means juggling providers, SDKs, rate limits, tokens, and vendor-specific APIs. Uniport simplifies that by offering:

* ✅ A **single API** that supports **text**, **image**, **audio**, **embeddings**, and even **video**
* ⚡ Access to dozens of models from **OpenAI**, **Anthropic**, **Mistral**, **Cohere**, **Stability**, and more
* 🔁 Built-in **compatibility with OpenAI SDKs** — just change the base URL and go
* 🛠️ Plug-and-play SDKs, cURL, Postman, or integrations with tools like **LangChain**, **Rocode**, and **LiteLLM**

***

###  What Can You Do with Uniport?

Whether you're a solo founder building a chatbot or a team deploying AI at scale, Uniport offers everything you need.

####  Text Models

Use large language models (LLMs) like GPT-4, Claude, and Mistral for:

* Chatbots and assistants
* Summarization and rewriting
* Code generation
* Document analysis
* Reasoning and planning

####  Image Generation

Generate AI images using models like:

* **Stable Diffusion XL** (for art, design, marketing)
* **DALL·E 3** (for commercial visual storytelling)

####  Audio AI

* **Text-to-Speech** using models like XTTS and Bark
* **Speech-to-Text** with Whisper and other STT models

####  Video Generation *(Beta)*

Create short-form videos from text prompts using state-of-the-art video diffusion models.

####  Embeddings

Turn text into vectors for:

* Semantic search
* AI-powered recommendations
* Clustering and matching

####  Moderation

Detect unsafe, biased, or harmful content before it reaches your users — all via one consistent moderation endpoint.

***

###  Why Uniport Exists

AI is evolving rapidly, but access is still fragmented:

* Some APIs are locked behind waitlists
* Some models lack structured docs or cost transparency
* Some providers charge unpredictable fees

**Uniport solves this** by offering:

* 🔓 Open, no-wait access to the best models
* 💡 Transparent pricing and latency metrics
* 🔁 Side-by-side comparisons of model output, cost, and speed
* 💼 Built for both **hobbyists** and **enterprises**

***

###  Built for Developers

Uniport is designed to be **developer-first**:

* No new SDKs to learn
* Just switch your `baseURL` to `https://api.uniportai.site/v1`
* Works out-of-the-box with `openai`, `langchain`, `rocode`, and `cline`

####  Integrates with:

* Frontends: React, Next.js, Vue
* Backends: FastAPI, Node.js, Flask
* Low-code: Zapier, Make.com, Retool
* AI agents: ElizaOS, Agno, AutoGen

***

### 💡 Why Use Uniport Instead of Others?

| Feature                       | Uniport AI          | OpenAI | OpenRouter | Replicate  |
| ----------------------------- | ------------------- | ------ | ---------- | ---------- |
| Multiple Model Providers      | ✅                   | ❌      | ✅          | ✅          |
| Unified API Format            | ✅                   | ✅      | ✅          | ❌          |
| Audio + Video Support         | ✅                   | ❌      | ❌          | ❌          |
| Real-Time Performance Metrics | ✅                   | ❌      | ❌          | ❌          |
| SDK Compatibility             | ✅ OpenAI-Compatible | ✅      | ✅          | ❌          |
| Transparent Token Costs       | ✅                   | ⚠️     | ⚠️         | ✅          |
| Open Access                   | ✅ No waitlists      | ❌      | ✅          | ⚠️ Limited |

***

###  Scalable, Secure & Global

* 🌐 Hosted on fast global edge servers
* 🔐 Encrypted, token-authenticated API keys
* 📊 Rate-limited by key — not by IP
* 📦 JSON-based input/output, easy to log or inspect
* 🚀 Scales from MVPs to production apps

***

###  Who Is Uniport AI For?

* 🧑‍💻 **Developers** building apps with AI models
* 🧪 **Researchers** testing models across modalities
* 🏢 **Startups & Enterprises** looking to experiment safely with powerful LLMs
* 🛠️ **Tooling Builders** integrating AI into developer workflows
* 📈 **Analysts & Data Teams** performing semantic analysis at scale

***

###  Quickstart Summary

> Using Uniport AI is as easy as:

```bash
curl https://api.uniportai.site/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {"role": "user", "content": "Summarize the last 5 years of AI progress."}
    ]
  }'
```

***

###  What Makes Us Different?

* 🧩 Model-neutral: We don’t build models — we help you use the best ones.
* ⚙️ Dev-friendly: Works with your favorite SDKs out of the box.
* 📊 Transparent: You always know what you're using, how much it costs, and how it performs.
* 🌍 Global: Designed for creators, teams, and businesses around the world.

***

###  Final Word

**Uniport AI** isn’t just another model hub. It’s the easiest way to **use**, **compare**, and **scale** the best models — without vendor lock-in, without complexity, and without limits.

Whether you're building the next AI-powered app or integrating models into your business stack, **Uniport puts the AI universe at your fingertips.**


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://uniport-ai.gitbook.io/docs/overview/what-is-uniport-ai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.