> For the complete documentation index, see [llms.txt](https://docs.nexos.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nexos.ai/workspace/chat.md).
# nexos.ai Chat
Learn how nexos.ai Chat works. Pick a model or let Auto choose, adjust settings like temperature and system prompts, and compare models side by side.
nexos.ai Chat lets you start a conversation with any model from a single interface. Pick a model manually or let Auto select the best fit for your prompt, then refine responses with advanced settings like temperature and system prompts.
## Getting Started
Starting an [AI chat](https://nexos.ai/features/ai-chat/) takes three steps: open a new chat window, choose the model that fits your task, and enter your prompt.
{% stepper %}
{% step %}
### Click **New chat**
Click **New chat** on the left side of the screen.
{% endstep %}
{% step %}
### Choose your preferred model
Choose a model from the selection window (see image below), or select **Auto** to let nexos.ai choose the best model for your request based on context and your workspace rules.
Each model shows context window size, supported inputs, and supported outputs.
Match your task to the model's capabilities. For images, choose models like DALL-E with image output. For text, any text-output model works.
{% hint style="info" %}
Tech details info:
* Context window: measured in tokens, determines how much text can be processed
* Input types: text, image, audio, file compatibility
* Output types: text, image, code generation capabilities
{% endhint %}
{% endstep %}
{% step %}
### Begin your conversation
Enter your prompt in the chat interface. Use web search (click **Web search**) to enhance results with current information. Upload files (click the **+** icon) or images to include additional context in your conversation. See example below:
{% endstep %}
{% endstepper %}
## Advanced options
This is completely optional, if you'd like - you can configure these settings to customize how the AI responds and behaves in your chat.
{% stepper %}
{% step %}
### Max completion tokens
Limits the length of the AI's response.
{% endstep %}
{% step %}
### Temperature
Controls response randomness. Lower values (0.1) produce more focused answers, higher values (0.9) create more **creative** responses.
{% endstep %}
{% step %}
### Top P
Narrows word choices during generation. Lower values make responses more predictable.
{% endstep %}
{% step %}
### System prompt
Sets the AI's behavior and role before the conversation starts. Acts as instructions for how the assistant should respond.
{% endstep %}
{% endstepper %}
## Token usage
Every conversation now shows your real-time costs at the top right of each Chat. See total cost, average per message, and conversation length so you know exactly where your budget is going.
---
# 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://docs.nexos.ai/workspace/chat.md?ask=&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.
