Frequently asked questions about BLUN
Here you will find clear answers about BLUN models, products, plans, context windows, agents, MCP servers, and the API. Each answer explains only the essentials and leads directly to the matching detail page when needed.
General questions
What is BLUN?
BLUN is a shared platform for AI models, digital products, and agents that work independently. The models process text, code, speech, and images. The products turn this into websites, web apps, desktop software, mobile apps, and real development work. The API, agents, and MCP Server connect BLUN to further applications and tools.
What is the difference between models, products, and the platform?
A model delivers intelligence. King, Voice, and Imagine understand tasks and produce suitable results.
A product is the working environment in which this intelligence is used. BLUN Apps builds web apps, BLUN Software develops desktop and mobile applications, and BLUN Code works directly on software projects.
The platform connects everything. This includes agents, the MCP Server, the API, documentation, and system status.
Why does BLUN use several web addresses?
BLUN separates public information from the actual working environments. On blun.ai models, products, the platform, pricing, and frequently asked questions are explained. Specialized areas use their own subdomains so that applications, accounts, and technical access points remain clearly separated.
- blun.ai is the public main site.
- api.blun.ai is the direct API access point and the developer portal.
- apps.blun.ai is the working environment for BLUN Apps and the Website Builder.
- chat.blun.ai opens the BLUN Chat.
- account.blun.ai manages sign-in, account, plans, billing, and downloads.
The different addresses belong to the same BLUN platform. Users do not need a separate independent BLUN system for each address.
Which BLUN address should I use?
If you first want to learn about BLUN or compare models and products, start on blun.ai. To talk with a model, use chat.blun.ai. A web app or website is started under apps.blun.ai . Developers use api.blun.ai, while personal settings, plans, and downloads are managed under account.blun.ai .
Is api.blun.ai just a documentation page?
No. api.blun.ai is both the technical starting point for developers and the direct base address for API requests. In the browser, documentation, access points, and integration help are shown. Applications call the intended API endpoints directly under the same domain.
Can search engines find my chats, projects, or account data?
No. Public product descriptions may be indexed, but private workspaces may not. Chat histories, app projects, account and payment data, API keys, drafts, and internal agent runs are protected by sign-in and permissions and are additionally kept out of the public search index.
Do I have to choose myself which model handles each task?
Not necessarily. In many BLUN products, the suitable capability level can be used based on the task. Users can choose a specific model when they want to keep control over it. In guided workflows, BLUN can also split the work sensibly between King, Voice, and Imagine.
Can I use BLUN without programming skills?
Yes. BLUN Apps, the Website Builder, and many agent workflows are built so that goals and requirements can be described in plain language. The guided process helps fill in missing information and makes technical decisions understandable.
BLUN Code and direct API integrations are additionally aimed at developers and technical teams who want to dig deeper into source code and systems.
Do I have to install anything?
It depends on the product. BLUN Chat, BLUN Apps, the Website Builder, agents, documentation, and system status can be used in the browser. BLUN Code Desktop is installed as a desktop application. The BLUN Code CLI is set up locally for working in the console. The API and MCP Server are integrated into the respective technical environment.
Can I start small and expand the project later?
Yes. A project can begin with a clear core function and later be extended with further pages, roles, data, platforms, or agents. The guided specification process ensures that extensions build on a traceable foundation.
Where do I find pricing and current availability?
Current packages, features, and availability are listed on the BLUN pricing page. Model and product descriptions should not contain hard-coded prices so that they do not become outdated or show conflicting information when things change.
Where are BLUN services operated?
BLUN runs on its own infrastructure in Europe. Which data is stored and processed for a specific product must additionally be described in the respective privacy information and contractual documents.
Why does BLUN no longer use version numbers publicly?
The stable product names King, Voice, Imagine, Apps, Software, and Code are meant to stay understandable and permanent for users. Technical model identifiers may still be necessary for API compatibility, but they belong in the developer documentation and not in general product communication.
Questions about the BLUN models
When should I use King?
King is the right choice for particularly complex, long-running, or still unstructured tasks. This includes large software projects, difficult analyses, extensive document collections, and agents that work across many interdependent steps.
How large is King's context window?
King has a context window of 1,000,000 tokens. This allows it to process very large document collections, long project histories, and extensive code areas within a single connected working context.
How large is the context window in the free and the paid plan?
| Model | Free tier | Paid plan |
|---|---|---|
| King | up to 1,000,000 tokens | up to 1,000,000 tokens |
| Voice | no token context window | no token context window |
| Imagine | no token context window | no token context window |
King thus provides its full context window even in the free tier.
The context window covers not only the latest user input. The previous conversation history, uploaded or inserted content, system instructions, tool results, and the generated response also require tokens. The maximum possible file size or pure input length is therefore below the full context window when space must be reserved for system information and the response.
Voice and Imagine are not limited by a text context window. For these models, the speech and image capabilities they include must be stated in the pricing overview.
Why is the context window not the only thing that matters?
The context window describes how much information a model can take into account within a task. It does not by itself describe reasoning ability or working style. King is designed for maximum complexity and long-running agents.
Can Voice only transcribe?
No. Voice supports both directions: Speech-to-Text converts spoken language into text, Text-to-Speech generates spoken output. In addition, Voice can be used for real-time interaction and speech-based agents.
Can Imagine edit existing images?
Yes. Imagine can create new images from text and develop existing motifs further based on instructions. This includes, for example, background changes, variants, color adjustments, new formats, and adding or removing parts of an image.
Which model suits large volumes of short tasks?
King is intended for this. It processes clearly defined tasks efficiently, even in large volume. Difficult or unclear cases remain traceable within the same workflow.
Questions about BLUN Apps and the Website Builder
Does BLUN Apps really create an application or just a plan?
BLUN Apps creates a working web app. User journeys, screens, and technical requirements are important intermediate steps, but not the end result. The approved specification is used as the basis for pages, data, roles, permissions, and features.
Why does BLUN Apps work with a guided process?
An app consists of more than a nice landing page. Without clear requirements, roles, data, permissions, or important states are often missing later. BLUN Apps asks about these points early and records them as a binding foundation. This leaves less to chance and keeps the result consistent even with later changes.
What applications can I create with BLUN Apps?
Typical projects are customer portals, internal tools, dashboards, booking flows, member areas, order overviews, support portals, forms, small administrative applications, and individual web platforms.
Does an app created with BLUN Apps run on smartphones?
Web apps are built responsively and can be used in the browser on desktop, tablet, and smartphone. When an installable app for iOS or Android with platform-specific features is needed, BLUN Software is the right environment.
What is the difference between the Website Builder and BLUN Apps?
The Website Builder is the specialized area within BLUN Apps for websites, landing pages, and funnels. BLUN Apps goes further and creates applications with user accounts, data, roles, permissions, and its own application logic.
Can a website become a web app later?
Yes. Because the Website Builder and web app creation live in the same product environment, pages can later be extended with sign-in, data, dashboards, and interactive flows. The exact extension follows the new product specification.
Can BLUN Apps map user accounts and different roles?
Yes. User accounts, roles, and permissions can be part of the specification. This defines which users can see which data and which actions they are allowed to perform.
Is BLUN Apps also suitable for internal company tools?
Yes. Many internal processes are especially well suited for guided web apps: approvals, lists, status tracking, forms, tasks, customer management, and reporting can be brought together in one central browser-based application.
Questions about BLUN Software
For which systems can BLUN Software create applications?
BLUN Software is intended for applications on Windows, macOS, iOS, and Android . At the start of the project, it is determined which target platforms are actually needed.
Does my application have to appear on all four platforms?
No. A project can be planned for Windows only, for mobile devices only, or for any combination of the supported platforms. BLUN Software helps identify shared features and the necessary platform-specific adjustments.
What is the difference between BLUN Apps and BLUN Software?
BLUN Apps creates browser-based web apps. BLUN Software develops installable applications for desktop and mobile devices. Software is the right choice when operating system features, local files, device access, app packages, or publication on the respective platforms are needed.
Does BLUN Software account for differences between desktop and mobile devices?
Yes. Desktop and mobile devices differ in navigation, screen size, input, permissions, and system features. A shared product logic can be preserved while the experience is designed appropriately for Windows, macOS, iOS, and Android.
Can an app use the camera, microphone, location, or notifications?
Such device features can be considered in the product specification. BLUN Software also plans the necessary permissions and the understandable user guidance around access.
Does BLUN Software publish automatically to app stores?
BLUN Software prepares the project, the builds, and the required publication steps for the chosen platforms. The final publication follows the rules of the respective platform and is done through the accounts responsible for it. Approvals and legal details remain under the control of the person responsible for the project.
Can I continue working on the generated project with developers later?
Yes. The software project can be developed further technically in BLUN Code and edited by a development team. The specification, features, and platform goals remain the shared foundation.
Questions about BLUN Code
Is BLUN Code available as a desktop application and as a CLI?
Yes. BLUN Code Desktop offers a graphical workspace for projects, files, changes, and agent tasks. The BLUN Code CLI works directly in the console and in the current project directory.
Does BLUN Code change real files?
Yes. When BLUN Code is given access to a workspace, it can read, create, and modify project files in a targeted way. Changes should remain visible and verifiable before they are published.
Can BLUN Code run terminal commands?
Yes. The CLI and appropriately configured workspaces can run commands, tests, builds, and diagnostic tools. Which commands are allowed depends on the permissions of the respective environment.
Does BLUN Code work with existing projects?
Yes. BLUN Code can examine an existing project structure, find relevant files, and take existing rules into account. It is suitable for debugging, new features, refactoring, tests, and technical documentation.
Does BLUN Code only produce suggestions, or does it complete tasks fully?
BLUN Code is meant for real implementation. It can analyze a requirement, plan changes, edit files, run checks, and summarize the result. A task should count as complete not just because code was generated, but only after suitable tests and checks.
Which BLUN model does Code use?
BLUN Code relies on King for complex architectures and large multi-step tasks. The project context remains available within the workflow.
Can BLUN Code publish or deploy a project?
Publications and deployments should only be performed when the corresponding workflow has been explicitly set up and approved. By default, changes remain controllable so that a user or responsible team can review them before publication.
Who is the desktop application for, and who is the CLI for?
The desktop application suits users who want to track tasks, changes, and results visually. The CLI is ideal for developers who work directly in the terminal, want to keep existing tools, or want to integrate BLUN into local and automated workflows.
Questions about BLUN agents
What is the difference between a chat and an agent?
A chat primarily answers an input. An agent receives a goal, a scope, tools, boundaries, and check criteria. It can plan several steps, perform actions, check intermediate results, and deliver a traceable completion.
Can several agents work together?
Yes. Different agents can take on their own roles and hand over results in a controlled way. Clear responsibilities are important so that several agents do not work on the same area in conflicting ways at the same time.
May agents make changes automatically?
Only within their configured permissions. An agent can be limited to read-only access, make changes only in a specific project, or require human approval before critical actions.
How is it prevented that an agent works outside its task?
Role, goal, tools, and boundaries are defined in advance. In addition, permissions can be limited on the tool being used or through the MCP Server. For unclear or blocked actions, the agent must hand the task over or request approval.
How can I tell what an agent has done?
An agent should summarize results, the tools used, the executed steps, verification evidence, and open points. This keeps it visible whether only a suggestion was created or the task was actually executed and controlled.
Questions about the BLUN MCP Server
What is the BLUN MCP Server in simple terms?
The MCP Server is the connection between BLUN and other tools. It tells a model or agent which functions are available, which inputs they need, and which actions are allowed.
Do I need the MCP Server to use BLUN?
No. BLUN models and products can also be used without your own MCP integration. The MCP Server is needed when external files, systems, APIs, IDEs, or your own tools are to be integrated into an agent workflow in a controlled way.
Can I use the MCP Server in an IDE?
Yes. The BLUN MCP Server is designed for integration into compatible IDEs and agent runtimes. This makes BLUN tools available directly in existing technical working environments.
Does an agent automatically get full access through MCP?
No. Tools can be limited to specific actions, projects, and data areas. An agent only sees and uses the functions made available to it in the respective workflow.
Can I connect my own internal systems?
Yes. Your own APIs, data sources, and company functions can be provided as clearly described tools. Permissions, inputs, results, and error cases should be clearly defined.
Is tool usage traceable?
The MCP Server creates a structured interface for tool calls. This makes it visible which tool was used with which inputs and which result came back. The concrete logging depends on the respective integration and configuration.
Questions about the BLUN system status
What does the status page show?
The status page shows the availability of important BLUN services. These currently include website, login, chat, API, Voice, and Imagine. The areas are checked separately so that a single outage remains recognizable.
How often is the status updated?
The status page updates itself automatically every minute.
What should I do if a service is shown as unavailable?
Wait briefly and check the page again. If the service repeatedly remains unavailable, the problem can be reported through the contact area. Name the affected service and the time of the outage.
What does it mean when the status page shows everything as available but my project still does not work?
The status page checks central services, but not every individual project configuration. In this case, access, permissions, local connection, and error messages should be checked in your own project. For persistent problems, support can help more precisely with this information.
Will further services be shown in the future?
With the public availability of further platform areas, the status page should additionally list BLUN Apps, Software, Code, agents, and the MCP Server separately. This keeps it visible, even on a larger platform, which specific area is affected.
---
Prices
Four tiers. One central contract.
All four tiers are on the central BLUN waitlist. There is no purchase and no charge yet.