> For the complete documentation index, see [llms.txt](https://docs.servoy.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.servoy.com/reference/servoy-cloud/cloud-control-center/add-ons.md). # Add-Ons ## Overview Add-Ons page where you can manage your ServoyCloud Add-ons. You can enhance and customize your experience by adding new features and functionalities to your namespace. ## Cloud Printing In the Add-Ons page, you will find the "Cloud Printing" section. Here, you can generate your [PDF Export](https://github.com/Servoy/svyUtils/wiki/Smart-Doc-Editor-Utils#pdf-export) [API key](https://github.com/Servoy/svyUtils/wiki/Smart-Doc-Editor-Utils#api-key) or upgrade your plan. ### Get started To begin using this Add-On, you need to familiarize yourself with the [Smart Doc Editor](https://github.com/Servoy/smartDocumentEditor/wiki) in your application. Once you have set it up, you can convert content from the Smart Doc Editor into PDFs, using the Export API and your API key. ### Plans #### Limited plan The "Limited Plan" provides free access to the PDF export service, but it is limited to 25 prints per day. This plan is suitable for testing or when you have only a few documents to convert. #### Unlimited plan For high-volume production scenarios or when you require a dedicated document server, we offer a paid plan. The "Unlimited plan" provides unlimited printing capabilities and dedicated resources to ensure seamless and efficient document conversion.\ For more info please contact ### Credentials #### Generate Key Getting your API key for the PDF Export service is easy. Just click the `Generate Key` button, and the key will be generated for you. Once you have your API key, you can use it for a specified period to generate and print PDF documents with the Smart Doc Editor. ## Servoy AI {% hint style="info" %} ServoyAI is currently in closed beta. Contact us if you'd like early access. {% endhint %} **AI that actually knows Servoy.** ServoyAI brings AI-assisted development right inside Servoy Developer — chat with your code, fix tickets end-to-end, and write JSUnit & Cypress tests. The AI understands your specific Servoy project: forms, relations, valuelists, and database structure. ### Plans The ServoyAI setup has two steps: **Step 1: Choose a plan** Select a plan that matches your team's usage intensity: * **Starter** — For occasional use, a few AI sessions per week. Includes questions & code explanations, understanding forms, flows & Servoy concepts, and light refactoring & code generation. * **Pro** — For developers using AI every day. Includes full agentic coding sessions, regular test, report & ticket generation, and consistent AI pair-programming. * **Premium** — For power users running agents all day. Includes high-volume agentic workflows and large-scale codebase refactoring. **Step 2: Assign developer seats** Assign seats to the developers who need AI access. Only developers who actually log in to Servoy Developer need a seat — Observers and admins don't. Billing is per developer seat, monthly. The AI budget is shared across the entire team — if you have 5 seats, all 5 developers draw from one combined pool.
ServoyAI subscription plans showing Starter, Pro, and Premium tiers with developer seat allocation

ServoyAI plans and developer seat management

### Developer Seats Manage which developers in your namespace have access to ServoyAI. Assign seats to specific users by email address. You can add or remove seats at any time — changes are pro-rated mid-month. The credit budget bar at the top shows team-wide consumption so you can monitor usage across your namespace.
ServoyAI developer seats management showing assigned users and credit usage

ServoyAI developer seat assignment

### Getting Started 1. Navigate to **Add-Ons > Servoy AI** in the Cloud Control Center 2. Choose a plan that fits your team 3. Assign developer seats to your team members 4. Each developer receives setup instructions for their IDE {% hint style="info" %} Managing Servoy AI plans and seats requires the **manage\_addons** permission. Users without this permission can view the page in read-only mode. {% endhint %} ## Private AI Hosting **Privacy-first AI, inside ServoyCloud.** Call frontier and open models hosted on Servoy's private infrastructure directly from your server and runtime plugins. No need to set up your own AI server, manage GPU infrastructure, negotiate model provider contracts, or worry about data leaving your environment. Pay-as-you-go from a prepaid credit balance — no commitments, no minimum spend. * **Zero data retention** — Your prompts and outputs are never stored. Once a response is returned, all request data is discarded * **Zero operator access** — No one at Servoy or any model provider can access your inputs or outputs * **No training on your data** — Your data is never used to train, fine-tune, or improve any model * **Encrypted end-to-end** — All data is encrypted in transit and at rest * **Region**: EU (Sweden) * **Data stays in-region** — Your data never leaves the Servoy Cloud boundary Navigate to **Add-Ons > Private AI Hosting** to get started.
Private AI Hosting dashboard showing credit balance, API tokens, and available models

Private AI Hosting overview

### Credit Balance Fund your usage with prepaid credits. Top up in fixed increments (€50 / €100 / €250 / €500) charged to your card on file. A small processing fee applies (1.5% + €0.25 per transaction). Enable **auto-recharge** so your service never halts unexpectedly: when the balance drops below a threshold you set (default €25), the system automatically tops up by a configured amount (default €100). {% hint style="warning" %} When your credit balance reaches €0, API requests are rejected until you top up. {% endhint %} ### Model Catalog The page shows all available AI models with pricing per 1 million tokens (input and output). Click any model name to copy it to your clipboard for use in your code. The catalog updates automatically — when new models are added, they appear on your next page load. The API is fully compatible with the [Servoy AI plugin](/reference/servoyextensions/server-plugins/ai.md) — use `plugins.ai.createOpenAiChatBuilder()` with the Private AI base URL and your token. No additional libraries or configuration needed. ### API Tokens Create API tokens to authenticate your application against the Private AI endpoint. You can create one token per app or integration to track usage independently. The token overview shows each token's name, spend and request count over the last 30 days, spend limit, and status (Active or Blocked). You can block or unblock tokens instantly from this view. {% hint style="info" %} Create one key per app or integration so you can track usage and set limits independently. {% endhint %} Use the token in your Servoy solution: ```javascript let AI = plugins.ai.createOpenAiChatBuilder() .baseUrl('https://genai.servoy-cloud.eu/v1') .apiKey('YOUR TOKEN') .modelName('YOUR MODEL') .build() AI.chatSync('Who are you?').getResponse() // runs privately inside ServoyCloud — no data leaves the platform ``` --- # 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://docs.servoy.com/reference/servoy-cloud/cloud-control-center/add-ons.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.