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

# 1.6: Sunflower

> Released: September 21, 2025

## What's new in 1.6?

<Card title="" img="https://mintcdn.com/aithing/ymZuY2hcYq_i4O0e/images/v1/index.png?fit=max&auto=format&n=ymZuY2hcYq_i4O0e&q=85&s=8ddabf29e827e9f8f096acd914dcebb9" width="2210" height="1120" data-path="images/v1/index.png" />

### Completely Free

[AI Thing](https://aithing.dev) is now fully **BYOK** — bring your own key and use it completely free.

### [Managed GitHub Agent](../features/v1/multiple-agents#github-agent) and many more...

The most **private** GitHub integration yet. Choose only the capabilities you want, and AI gets **just enough permissions to do the job — nothing more.**

Use the GitHub Agent to manage repositories, issues, pull requests, workflows, and more — all directly from AI.

<Columns cols={3}>
  <Card title="Asana" />

  <Card title="Atlassian" />

  <Card title="Canva" />

  <Card title="GitHub" />

  <Card title="Google" />

  <Card title="HubSpot" />

  <Card title="Hugging Face" />

  <Card title="Intercom" />

  <Card title="Linear" />

  <Card title="Monday.com" />

  <Card title="Netlify" />

  <Card title="Notion" />

  <Card title="PayPal" />

  <Card title="Sentry" />

  <Card title="Square" />

  <Card title="Stytch" />

  <Card title="Vercel" />

  <Card title="Webflow" />

  <Card title="Wix" />

  <Card title="Zapier" />
</Columns>

### View Agent Tools

You can now see exactly what tools each agent provides and what AI can do with them.

<Frame>
  <img src="https://mintcdn.com/aithing/ymZuY2hcYq_i4O0e/images/v1/view-tools.png?fit=max&auto=format&n=ymZuY2hcYq_i4O0e&q=85&s=dc170423d4ddf231e168e1a4031b9cc0" width="1514" height="570" data-path="images/v1/view-tools.png" />
</Frame>

### [Prompt Cache](/features/v1/managed-models#prompt-cache)

Reuses common parts of a prompt to **speed up responses** and **lower costs** in long or repetitive conversations.

### [Output Tokens](/features/v1/managed-models#output-tokens)

Control the maximum response length. Keep it short for **concise answers**, or expand for **detailed outputs**.

<Frame>
  <img src="https://mintcdn.com/aithing/ymZuY2hcYq_i4O0e/images/v1/preferences-models.png?fit=max&auto=format&n=ymZuY2hcYq_i4O0e&q=85&s=865c2276e8a74a4a261ede357c436f2c" width="1052" height="354" data-path="images/v1/preferences-models.png" />
</Frame>