IONOS Cloud AI Model Hub
Your gateway to a secure multimodal AI platform
- One platform for the most powerful AI models
- Fair and transparent token-based pricing
- No vendor lock-in with open source
Bring AI to life in few simple steps
-
Query:
Your query is sent to our powerful vector database to identify relevant information. -
Retrieve document:
The vector database accesses the data and retrieves the most relevant documents for your query. -
LLM prompt:
The retrieved documents are passed to your chosen large language model (LLM) to create a tailored response. -
Response:
The response generated by the LLM is returned and ready for immediate use.
The best AI for your applications in the IONOS Cloud
You're always a step ahead with the IONOS Cloud AI Model Hub.
Use case
Use case
Enrich text with AI-generated images
Generate engaging visuals from text prompts for better communication and impact.
- Derive book covers based on a book’s abstract
- Create eye-catching visuals to boost ad appeal
- Increase visibility and engagement on social media
Use case
Use case
Create knowledge databases for patents
Build an application that provides patents or other confidential information within your company.
- Import and store patents as plain text in ChromaDB
- Find relevant material with a search string
- Keep track of your data, always
Use case
Use case
Take your chatbot to the next level with AI
Use your company's internal knowledge base for chatbot-supported customer inquiries.
- Export articles as text and import them into a vector database
- Enhance customer engagement with quick, personalized responses
- Let the IONOS Cloud AI Model Hub's LLM handle valuable conversations
The IONOS Cloud in practice
Questions about the IONOS Cloud?
Sales support
1-484-424-7378
Our product experts are here from 9:00am–5:00pm, Monday to Friday.
Unleash the full power of AI securely and efficiently
The AI platform for accessing leading open source generative models for generating texts and images.
Top-level data security
Committed to reliability
- Safeguard your business data within the secure IONOS Cloud
- No third-party access to your personal data
- Reliable hosting in IONOS Cloud data centers
Wide variety of use cases
Add AI to your applications
- Analyse images, generate, summarise and translate text, or power conversational Q&A
- Power semantic search, build recommendation engines, and cluster data
- Generate visuals, mockups, and creative assets from text
Smarter answers
Vector search & RAG
- Built-in vector database for similarity-based searches
- Retrieval-augmented generation (RAG) tailors responses to your data
- Supports multilingual embedding models for broader coverage
Serverless and scalable
Adapts to your needs
- Pay only for what you use — per token
- Runs smoothly from early tests to large-scale production
- No need to manage infrastructure or operations
Leading models
Options for every use-case
- Up to date with the latest and most reliable AI models
- Best-of-breed international or European sovereign options
- Access to open-source models with no licence fees
Seamless integration
Familiar interfaces
- OpenAI-compatible REST API for a quick start
- Works with standard frameworks and coding languages
- Playground in the DCD for model testing
Fair pricing based on usage
Benefit from a token-per-use pricing model.
Large language models
Model | Price per 1 million input tokens | Price per 1 million output tokens
|
|---|---|---|
Llama 3.1 8B Instruct
| $0.17 | $0.17
|
Mistral Nemo Instruct | $0.17 | $0.17
|
Mistral Small 24B Instruct | $0.11 | $0.33
|
gpt-oss-120b | $0.17 | $0.71
|
Llama 3.3 70B Instruct
| $0.71 | $0.71
|
Llama 3.1 405B Instruct | $1.93 | $1.93 |
Llama 3.1 8B Instruct
| |
|---|---|
Model | |
Price per 1 million input tokens | $0.17 |
Price per 1 million output tokens
| $0.17
|
Mistral Nemo Instruct | |
Model | |
Price per 1 million input tokens | $0.17 |
Price per 1 million output tokens
| $0.17
|
Mistral Small 24B Instruct | |
Model | |
Price per 1 million input tokens | $0.11 |
Price per 1 million output tokens
| $0.33
|
gpt-oss-120b | |
Model | |
Price per 1 million input tokens | $0.17 |
Price per 1 million output tokens
| $0.71
|
Llama 3.3 70B Instruct
| |
Model | |
Price per 1 million input tokens | $0.71 |
Price per 1 million output tokens
| $0.71
|
Llama 3.1 405B Instruct | |
Model | |
Price per 1 million input tokens | $1.93 |
Price per 1 million output tokens
| $1.93 |
Vision-Language Models
Vision-Language Models for professional OCR. Convert documents, invoices, and tables into structured Markdown, LaTeX, or JSON. Ideal for data extraction from complex forms and digitizing enterprise archives.
Model | Price per 1 million input tokens | Price per 1 million output tokens
|
|---|---|---|
LightOnOCR 2 | $ 0.17 | $ 0.33 |
LightOnOCR 2 | |
|---|---|
Model | |
Price per 1 million input tokens | $ 0.17 |
Price per 1 million output tokens
| $ 0.33 |
Text-to-image
Price per image
| |
|---|---|
FLUX.1 [schnell] New | $0.032 |
FLUX.1 [schnell] New | |
|---|---|
Price per image
| $0.032 |
Embedding Models
Power RAG (Retrieval-Augmented Generation) and similarity search by converting text into vector embeddings for our built-in databases or your own solution. Costs apply only to input tokens (creation/queries), without charges for embedding model outputs.
Price per 1 million tokens
| |
|---|---|
paraphrase-multilingual-mpnet-base-v2 | $0.01
|
bge-large-en-v1.5 | $0.015
|
bge-m3 | $0.02 |
paraphrase-multilingual-mpnet-base-v2 | |
|---|---|
Price per 1 million tokens
| $0.01
|
bge-large-en-v1.5 | |
Price per 1 million tokens
| $0.015
|
bge-m3 | |
Price per 1 million tokens
| $0.02 |
Data collections storage
Price per 1 million tokens
| |
|---|---|
Storage | $0.011 / 30 days |
Storage | |
|---|---|
Price per 1 million tokens
| $0.011 / 30 days |
Code Models
Code Models for high-performance software development. Automate code generation, refactoring, and debugging across dozens of programming languages. Ideal for IDE integrations, agentic workflows, and complex codebase analysis.
Models | Price per 1 million input tokens | Price per 1 million output tokens
|
|---|---|---|
Qwen3-Coder-Next (80B) | $0.17 | $0.89 |
Qwen3-Coder-Next (80B) | |
|---|---|
Models | |
Price per 1 million input tokens | $0.17 |
Price per 1 million output tokens
| $0.89 |
A token typically represents a unit of text processed by an AI model during inference. It can be a word, character, or another unit, depending on the model and language.
Documentation and guides
Getting started
Get a complete overview and maximize your data with the IONOS Cloud AI Model Hub's first steps for successful integration and use.
API interface
Integrate the desired LLMs into your applications with the IONOS Cloud AI Model Hub API and optimize them. Find out everything you need to know here.
Enrich your apps
- Register for the IONOS Cloud Public Cloud
- Get full access to the IONOS Cloud AI Model Hub API
- Connect powerful AI models to your application
A variety of AI models with endless possibilities
Discover the advantages of our open-source-based AI solutions.
Generate high-quality content in seconds with an open-source language model from our AI Model Hub.
- Texts written like a native
- Creative writing and storytelling
- Code generation
Reduce lengthy articles, paragraphs, or documents to their essential points with LLMs.
- Summaries
- Abstracts
- Briefs
Use LLMs to select similar texts based on content or context and categorize them effectively.
- Sentiment analysis
- Topic labelling
- Tagging content
With the AI Model Hub, you can choose relevant texts based on predefined criteria and fine-tune the accuracy of search results.
- Implement a relevance ranking
- Enhanced query understanding with LLMs
Store and process text elements more efficiently than with SQL or NoSQL databases using a vector database.
- Identify relevant content for queries and searches
- Provide content to an LLM for processing
Benefit from precise and customized image generation with AI, creating unique visuals in no time.
- Convert existing texts into visual representations
- Create images based on text inputs