> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Chat

> Chat and test AI models in real time directly in Orq.ai, with full conversation history, file attachments, and access to your configured agents.

<Frame caption="Using the AI Chat">
  <img src="https://mintcdn.com/orqai/gDycPJzj9mP5VpLj/images/ai-chat.png?fit=max&auto=format&n=gDycPJzj9mP5VpLj&q=85&s=d3bbef229032b2a760ef49e9b689b2b2" alt="AI Chat" width="1739" height="1221" data-path="images/ai-chat.png" />
</Frame>

**AI Chat** gives your team one interface to chat with every model and agent in your workspace. No separate subscriptions or accounts needed.

* **Every provider, one place**: OpenAI, Anthropic, Google, Mistral, custom models, all in a single chat.
* **Switch models mid-conversation**: compare outputs across providers without leaving the thread.
* **Chat with your agents**: deploy agents built in Orq.ai directly into AI Chat for your whole team.
* **Files built in**: upload images, PDFs, and documents directly into the conversation.
* **Admin-controlled access**: scope available models and agents per workspace.

<Card title="Configure models and agents" icon="gear" href="/docs/ai-chat/configuration">
  Before your team can use **AI Chat**, a workspace admin must configure which models and agents are available. Start here.
</Card>

## Starting a Chat

1. Open **AI Chat** from the top-left product switcher.
2. Click <Icon icon="pen-to-square" /> **New Chat** in the sidebar to start a fresh conversation.
3. Select a model or agent using the selector in the input bar.
4. Type your message in the input box at the bottom.
5. Press **Send** or hit `Enter` to submit.

Past conversations appear in the left sidebar, named automatically based on the content of the exchange.

<Tip>
  Hover over any chat name and click <Icon icon="ellipsis" /> to rename or delete it.
</Tip>

## Models and Agents

The input bar includes a selector that lists all models and agents enabled by your workspace admin. Select the one you want before sending your message. You can switch mid-conversation.

* **Models** are sourced from your [AI Router](/docs/model-garden/overview), giving access to models across all configured providers.
* **Agents** are built in [AI Studio](/docs/agents/build) around specific use cases and can use tools, knowledge bases, and multi-step reasoning. **AI Chat** is a great way to test and validate agents before rolling them out to your team.

## Input Options

Click <Icon icon="circle-plus" /> in the input bar to open the options menu. Three options are available depending on the selected model or agent:

<Warning>
  Agents are pre-configured with their own model, tools, and settings. Thinking and Web Search cannot be toggled from the chat.
</Warning>

### <Icon icon="paperclip" />  Upload Photos & Files

Attach images, PDFs, and documents directly to your message. Maximum file size is 20 MB. Available for any model with vision or document capabilities.

### <Icon icon="globe" />  Web Search

<Note>Only available for models that support Web Search.</Note>

Toggle web search on or off. When on, the model retrieves up-to-date information from the web to ground its responses.

### <Icon icon="brain" />  Thinking

<Note>Only available for models that support Thinking.</Note>

When Thinking is enabled, the model reasons through the problem before writing its response. This improves accuracy on complex or multi-step tasks at the cost of additional tokens and latency. Selecting **Thinking** opens a submenu with two modes:

* **Standard**: the model applies a moderate level of reasoning.
* **Extended**: the model reasons more deeply, best suited for difficult problems that benefit from more thorough analysis.