> 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.
### 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. Each model has different strengths in speed, reasoning, creativity, and efficiency. This section outlines the available models and explains their intended use.
### OpenAI Models
* [GPT-4o](https://chatlyai.app/models/gpt-4o): A **multimodal model** capable of processing text, images, and other input types. Delivers strong reasoning, natural conversation, and high-quality content generation across multiple formats.
* [GPT-5.4](https://chatlyai.app/chat?utm_model=vgpt-g5-4)**:** An advanced evolution of the GPT-5 series focused on **stronger reasoning depth, improved long-context understanding, and more stable tool interactions**. Optimized for research, technical workflows, and large-scale knowledge processing.
* [GPT-5.4 Pro](https://chatlyai.app/chat?utm_model=vgpt-g5-4p): The highest-capability model in the GPT-5 family, offering **state-of-the-art reasoning, maximum reliability, and the strongest performance on complex scientific, mathematical, and multi-step problem solving tasks**. Designed for enterprise, research, and mission-critical AI systems.
* [**GPT-5.4 Mini**](https://chatlyai.app/chat?utm_model=vgpt-g5-4m)**:** A lightweight and efficient variant of the GPT-5.4 series, designed for fast responses and cost-effective performance while maintaining solid reasoning and contextual understanding. Optimized for everyday tasks, chat applications, and scalable workflows where speed and efficiency are key.
* [GPT-5.5](https://chatlyai.app/chat?utm_model=vgpt-g5-5): OpenAI’s latest flagship model, with stronger reasoning and broad general-purpose capability across coding, analysis, and knowledge work.
### Anthropic Models
* [Claude 4.6 Sonnet](https://chatlyai.app/models/claude-sonnet-4-6): Powerful model for coding, reasoning, and complex problem solving. It delivers state-of-the-art performance across real-world tasks and domain knowledge in finance, law, medicine, and STEM.
* [Claude 4.5 Haiku](https://chatlyai.app/models/claude-haiku-4-5): Anthropic’s fastest, cost-efficient model.
* [Claude 4.7 Opus](https://chatlyai.app/models/claude-opus-4-7): Anthropic's latest most capable AI model that excels at coding, agent tasks, and everyday work like research and document handling.
* [Claude 4.8 Opus](https://chatlyai.app/chat?utm_model=vgpt-cl1-5): Anthropic’s most advanced Opus model for complex coding, reasoning, and long-running agent tasks.
* [Claude Fable 5](https://chatlyai.app/chat?utm_model=vgpt-cl-f5): An Anthropic model available in Chatly, suited to creative and long-form writing tasks.
### Google Models
* [Gemini 3.1 Pro](https://chatlyai.app/chat?utm_model=vgpt-g3-1p): An upgraded iteration of Gemini 3 Pro with stronger deep reasoning across text, images and code. It refines 'Deep Think' for more accurate problem-solving, enhanced coding abilities, and more reliable research-backed answers.
* [Gemini 3.1 Flash Lite](https://chatlyai.app/chat?utm_model=vgpt-g3-1fl): A lightweight, ultra-fast model optimized for low-cost, high-throughput tasks and simple interactions. Ideal for quick responses and large-scale applications. ⚡
* [Gemini 3.5 Flash](https://chatlyai.app/chat?utm_model=vgpt-g3-5): Google’s latest ultra-fast multimodal model, optimized for real-time interactions and high-throughput tasks at scale.
### xAI Models
* [Grok 4](https://chatlyai.app/models/grok-4): The latest Grok release. Optimized for advanced reasoning and problem-solving.
* [Grok 4.1 Fast (Reasoning)](https://chatlyai.app/models/grok-4-1-fast): X.AI's most advanced artificial intelligence model to date, designed for high-level reasoning, real-time information access, and complex problem-solving.
* [Grok 4.3](https://chatlyai.app/chat?utm_model=vgpt-g4-3): A balanced model for everyday tasks — fast, accurate, and built for reliable performance across writing, analysis, and conversation.
### MoonShot AI Model
* [Kimi K2.6](https://chatlyai.app/chat?utm_model=vgpt-kk-2-6): A powerful long-context model built for deep document understanding, research, and multi-step reasoning at scale.
### MiniMax Models
* [MiniMax M3](https://chatlyai.app/chat?utm_model=vgpt-mm-m3): MiniMax’s flagship model for general reasoning, conversation, and content tasks.
### DeepSeek Model
* [DeepSeek V4](https://chatlyai.app/chat?utm_model=vgpt-ds4p): A high-performance open model optimized for coding, math, and complex reasoning with exceptional efficiency.
---
# 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://help.chatlyai.app/products-and-features/ai-chat/what-is-ai-chat.md?ask=&goal=
```
`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.