> 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/gateway-api/playground.md).

# Playground

### Overview

A playground is an environment where you can test your API key and our models. The playground calls the nexos.ai public API directly, so it runs on a key of your own rather than your workspace session.

### How to use it?

1. **Generate an API key**\
   If you haven’t already, generate an API key. Copy it and store it somewhere safe, as you won’t be able to retrieve it later.
2. **Open the Playground**\
   Click **Start Using the Playground** to get started.
3. **Add models**\
   Select one or more models you’d like to test and compare.
4. **Send a prompt**\
   Enter your prompt and send it to all selected models at once.
5. **Compare the responses**\
   Review the models’ answers side by side to see how they differ in quality, style, reasoning, or other aspects relevant to your use case.
6. **Follow the instructions**\
   Continue the conversation, refine your prompts, or adjust the models to find the best fit for your needs.

{% hint style="info" %}
This feature uses tokens from your token pool.
{% endhint %}

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2FepAVpc4NSc1AIQlewzHV%2FRecording%202026-10-20%20103940.gif?alt=media&amp;token=55a7fa1d-c881-4e49-9107-9f2e737b3274" alt=""><figcaption></figcaption></figure>

### Model parameters

Use model parameters to control how models generate their responses. You can adjust these settings globally or override them for individual models.

* **System prompt** - Set instructions that define how the model should behave, respond, or format its answers.
* **Temperature** - Controls how predictable or creative responses are. Lower values produce more consistent responses, while higher values introduce more variation.
* **Top P** - Controls the range of tokens the model considers when generating a response. Lower values make responses more focused, while higher values allow for more variety.
* **Frequency penalty** - Reduces repetition in responses. Higher values make the model less likely to repeat words or phrases it has already used.

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2F68Nweq7VZ3p72tslgLUA%2FRecording%202026-10-20%20105650.gif?alt=media&amp;token=18e92a8e-77b0-44c4-81e9-2387199d703f" alt=""><figcaption></figcaption></figure>

* **Override** - Use custom parameters for a specific model.
* **Reset to global** - Restore the model’s parameters to the global settings.
* **Apply to all** - Apply the current parameter settings to all selected models.

#### **How does it look?**

**Change it in global parameters:**&#x20;

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2F3w0TbVhcNo6leN223829%2FRecording%202026-10-20%20111529.gif?alt=media&amp;token=5fb63ae7-c6e0-48bf-ad3a-3d33daddb4a3" alt=""><figcaption></figcaption></figure>

**Override and Apply to all:**&#x20;

<figure><img src="https://4112003433-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDcOhapgXnoeDvgGQ8Jm4%2Fuploads%2F0gHJR0EtKJmeK23WaeSj%2FRecording%202026-10-20%20111824.gif?alt=media&amp;token=04a2b895-5b52-465e-a69a-bff1becd345b" alt=""><figcaption></figcaption></figure>


---

# 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/gateway-api/playground.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.
