Description
AI models hosted in Germany, working from your own content
IONOS AI Model Hub is a fully managed inference service from the German hosting provider IONOS. It gives on-demand access to language models, embedding models, a reranker, a text-to-image generator and OCR models through OpenAI-compatible APIs, without provisioning GPUs or running model servers.
A model does not know which products you sell, which texts are approved or which images you may use. That knowledge lives in Kontainer DAM & PIM.
When an app or agent built on AI Model Hub is connected to Kontainer through the Kontainer API or MCP, it can retrieve product data, metadata and file information whenever a task calls for it, instead of relying on copies that age.
IONOS states that all processing takes place in its German data centers and that input data is never used for model training.
Benefits
Why integrate IONOS AI Model Hub with Kontainer?
✔ Processing in Germany
IONOS states that AI Model Hub processing is confined to its German data centers, which suits organizations that want their AI workloads to stay in Germany.
✔ Input data is not used for training
According to IONOS, the data you send is used only for your own requests and is excluded from model training.
✔ Fully managed
There are no GPUs to provision and no model servers to maintain. You call the models through the API.
✔ Familiar APIs
OpenAI-compatible endpoints mean developers can reuse the clients and libraries they already know.
✔ Several model types in one place
Language models, embeddings, a reranker, image generation and OCR are available from the same platform.
✔ Kontainer as your Single Source of Truth
Let your AI solution work from the same approved product data and files as the rest of the organization.
Features
How IONOS AI Model Hub and Kontainer work together
✔ The Kontainer API
Retrieve and update product data, metadata and file information from apps and functions that call AI Model Hub.
✔ MCP for agents
An agent built on models from AI Model Hub can use Kontainer as a tool through the Model Context Protocol, without custom development for every agent.
✔ Tool calling
AI Model Hub lets models call external APIs and predefined functions, so a model can trigger a lookup in Kontainer while it works on a task.
✔ Embeddings and reranking for RAG
Multilingual embedding models and a reranker can turn product texts and metadata from Kontainer into a searchable knowledge base, for example in a PostgreSQL database with pgvector.
✔ OCR for documents
OCR models can read text from scanned documents and images of text, which can then be added to the files in Kontainer DAM as searchable metadata.
✔ Text generation for product content
Draft product texts, summaries and answers from approved product data in PIM.
✔ Product data and files from PIM and DAM
Use names, descriptions, specifications, categories, variants, images, videos and documents, together with their tags and metadata.
Set-up
Connect IONOS AI Model Hub and Kontainer in three steps
- Create an access token at IONOS
Generate an API token for AI Model Hub in your IONOS Cloud account and choose the models the solution should use. - Give your solution access to Kontainer
Create a JSON API token, or set up OAuth 2.0, for the Kontainer user the solution should act as. Access is limited to what that user may do. - Let the model reach Kontainer
Connect through MCP or expose Kontainer lookups as tools the model can call, and test with real product questions.
The set-up requires some technical or IT knowledge. The MCP guide describes the details.
Use Cases
What can you build with IONOS AI Model Hub + Kontainer?
- A multilingual product knowledge base
Let staff ask questions across product texts and documents in several languages, with answers grounded in approved content. - Searchable scanned documents
Extract text from scanned data sheets and manuals and make it findable through metadata in the DAM. - Product text suggestions
Generate drafts for missing product descriptions that your team reviews and approves. - Content for European markets
Adapt product texts to several languages, starting from localized data in Kontainer. - A product advisor
An assistant for sales, support or your webshop that answers from approved PIM data. - Agents across systems
Combine Kontainer with your ERP, CRM and other systems in the same workflow.
Support
Get started with IONOS AI Model Hub + Kontainer
Which data and workflows your AI solution needs decides how to set things up. Contact our support team for help with set-up, customization or best-practice advice.
You can write to us at support@kontainer.com
Read more about the Kontainer API and MCP for Kontainer DAM and PIM.
See IONOS’s AI Model Hub documentation.
For EU AI Act requirements, see Labelling AI-generated content in Kontainer and the EU AI Act (Regulation (EU) 2024/1689).
FAQ
What is IONOS AI Model Hub?
IONOS AI Model Hub is a fully managed inference service from the German hosting provider IONOS. It offers language models, embedding models, a reranker, a text-to-image generator and OCR models through OpenAI-compatible APIs, hosted in German data centers.
Can IONOS AI Model Hub be integrated with Kontainer?
Yes. Kontainer can be connected to solutions built on AI Model Hub through the Kontainer API and MCP, so models and agents can retrieve product data, metadata and file information from Kontainer DAM & PIM.
Can agents on AI Model Hub use Kontainer via MCP or tool calling?
Yes. An agent built on models from AI Model Hub can use an MCP client to reach Kontainer as a tool. Alternatively, Kontainer lookups can be exposed as tools, since AI Model Hub supports tool calling.
Can AI Model Hub use product data and files from Kontainer?
Yes. Product names, descriptions, specifications, categories and variants from PIM can be used as context, and images, videos and documents in DAM can be found through metadata and tags.
Can I build semantic search or RAG on Kontainer content?
Yes. Embedding models and a reranker from AI Model Hub can turn product texts and metadata from Kontainer into a knowledge base that a model draws on when it answers. IONOS recommends an external vector database for this, such as PostgreSQL with pgvector.
Can OCR be used on documents from Kontainer DAM?
Yes. A solution can send a document from Kontainer DAM to an OCR model and write the extracted text back as metadata through the Kontainer API, so the content becomes searchable.
Where is data processed, and is it used for training?
IONOS states that processing takes place in its German data centers and that input data is not used for model training. What reaches the model is decided by your solution, and access to Kontainer is limited to what the Kontainer user behind the connection may do.
Does our data need to be trained into an AI model?
Not necessarily. An integration can retrieve the relevant information from Kontainer when it is needed, through MCP or the API. That lets you work with current data without making it part of a model’s training.
How do we get started?
Start by clarifying which data and workflows the AI solution needs. Then contact Kontainer’s support team at support@kontainer.com for help with set-up, customization and best practices.