> For the complete documentation index, see [llms.txt](https://help.chatlyai.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.chatlyai.app/products-and-features/ai-chat/what-is-ai-chat.md).

# What is AI Chat?

The AI Chat tool allows you to interact with advanced language models to ask questions, draft content, analyze data, or brainstorm ideas. You can type requests, attach supporting files, and receive contextual responses in real time. Switch models at any time to compare answers, and pick the one that fits your task best.<br>

<figure><img src="https://3503370835-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FOHDPAn3RzU7mRQrMH1UK%2Fuploads%2FNDEFYCALFCVuBQylO66k%2Fimage.png?alt=media&#x26;token=0d068dc4-30a9-46fc-923d-20f00f6caaca" alt=""><figcaption></figcaption></figure>

### Input Types

**Text-to-Text**

* Enter queries in plain language.
* Supports both short prompts and multi-paragraph requests.

**Attachments**

* Supported file types: .jpg, .jpeg, .png, .gif, .webp, .pdf, .txt, .csv, .json, .md, .html, .docx, .pptx, .xlsx, .epub
* Supported image extensions
* File size: up to 20 MB per file.

Chatly supports a wide range of models from leading providers: **OpenAI**, **Anthropic**, **Google**, **xAI**, **DeepSeek**, **Moonshot AI** and **MiniMax**. Each model has different strengths in speed, reasoning, creativity, and efficiency, and a short description next to each one in the model picker helps you choose. Open the model picker in the chat box and type in **Search models** to find a model, or click **See more** for the full list.

<figure><img src="https://3503370835-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FOHDPAn3RzU7mRQrMH1UK%2Fuploads%2FlgOx286Am90cTcSWdOHj%2Fimage.png?alt=media&#x26;token=11deec07-dae9-4288-ac55-8775f149e98c" alt=""><figcaption></figcaption></figure>

### Anthropic Models

* **Claude Fable 5.2**: Newest Fable, frontier reasoning and agents.
* **Claude Opus 5.5**: Most capable Opus for complex challenges.
* **Claude Sonnet 5.5**: Frontier smarts at Sonnet speed.
* **Claude Haiku 5.5**: Fastest Claude, sharper than ever.
* **Claude 5 Opus**: Frontier agentic coding and enterprise work.
* **Claude 5 Sonnet**: Frontier coding and agents, Sonnet speed.
* **Claude Fable 5**: Frontier reasoning and agentic power.
* **Claude 4.8 Opus**: Most intelligent model for complex tasks.
* **Claude 4.7 Opus**: Most intelligent model for complex tasks.
* **Claude 4.6 Sonnet**: Best for coding and deep analysis.
* **Claude 4.5 Haiku**: Fast, concise model.

### OpenAI Models

* **GPT 6.1 Sol**: Flagship power for the hardest problems.
* **GPT 6 Astra**: OpenAI's newest frontier flagship.
* **GPT 5.6**: OpenAI's frontier flagship.
* **GPT 5.6 Sol**: Flagship power for the hardest problems.
* **GPT 5.6 Terra**: Balanced power for everyday work.
* **GPT 5.6 Luna**: Fastest responses in the GPT 5.6 family.
* **GPT 5.5**: Ultimate reasoning, complex task planning.
* **GPT 5.4 Pro**: Highest-precision GPT-5.4 variant.
* **GPT 5.4**: Ultimate reasoning, complex task planning.
* **GPT 4o**: Versatile multimodal content generation.

### Google Models

* **Gemini 4 Carbon**: Gemini 4 generation, frontier reasoning.
* **Gemini 4 Argon**: Next-gen Gemini, frontier reasoning.
* **Gemini 3.1 Pro**: Deep research and multi-step logic.
* **Gemini 3.6 Flash**: Sharper Flash, leaner outputs.
* **Gemini 3.5 Flash**: Frontier intelligence, Flash speed.
* **Gemini 3.5 Flash Lite**: Fastest Gemini, built for volume.
* **Gemini 3.1 Flash Lite**: Ultra-fast, light, efficient utility.

### xAI Models

* **Grok 4.5**: Opus-class reasoning, token-efficient.
* **Grok 4.3**: Expanded context, deeper reasoning.
* **Grok 4**: Sharp logic, unfiltered insights.

### Moonshot AI Models

* **Kimi K3**: Open-weight frontier agentic coding.
* **Kimi K2.6**: Long-context reasoning and analysis.

### DeepSeek Models

* **DeepSeek V4**: Sharp reasoning, deep analysis.

### MiniMax Models

* **MiniMax M3**: Agentic reasoning and efficient coding.

The list changes as new models are added. The model picker always shows the current models.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.chatlyai.app/products-and-features/ai-chat/what-is-ai-chat.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.