Navigate Through the Mendix Cloud GenAI Portal

Last modified: June 25, 2026

Introduction

The Mendix Cloud GenAI portal is the part of the Mendix portal that provides access to Mendix Cloud GenAI Resource Packs. After logging in, you can navigate to the overview of all resources. You can see all resources that you are a team member of and access their details.

Overview

After clicking a specific resource, you land on its details page, which provides shortcuts to consumption insights, key generation, team management, and helpful documentation.

Consumption (Only for Text and Embeddings Generation Resources)

The Consumption tab is available for Model resources only.

The Consumption tab provides an overview of GenAI Unit and Large Language Model (LLM) token consumption for the resource. Use this overview to see current usage, view daily consumption insights, and compare the current period with previous periods.

Note that periods represent bundle months. A bundle month is the period during which consumption is tracked, beginning on the date of your last GenAI Resource entitlement reset and ending on the next reset date. This creates a recurring monthly cycle based on your resource activation date, not the calendar month.

Current Consumption shows the total GenAI Units consumed against your monthly allocation, displayed as a percentage and a number (for example, 1,521 / 1.6k). Plan shows the resource pack model type (for example, Anthropic Claude Opus) and the total GenAI Unit allocation for the bundle month. The bundle refill date is shown at the top of the page.

Below the summary, the page shows Consumption Over Selected Time Range. You can switch between weekly (W), bundle month (BM), month to date (MTD), and six months (6M) views. The charts show:

Monthly Bundle GenAI Units Consumption – GenAI Units consumed per day, with a dashed line indicating the monthly allocation limit.
Monthly Bundle Input Consumption – Raw LLM input tokens consumed per day.
Monthly Bundle Output Consumption – Raw LLM output tokens consumed per day.
Monthly Bundle API Calls – Number of API calls made under the resource per day within a bundle month.

What Are Tokens and GenAI Units?

LLM tokens (not to be confused with Mendix Cloud Tokens) are what you pay for when consuming large language model services. Text input is first "tokenized," meaning it is broken down into smaller pieces where each piece represents a token. A good rule of thumb is that 100 tokens are around 75 English words, though this varies by model and language. Tokens sent to the model are called input tokens; tokens generated by the model are called output tokens.

GenAI Units are the unit of measure for consumption across all models on a resource. Each model family has a different exchange rate. The exchange rate is the number of GenAI Units consumed per one million input or output tokens. A more capable model costs more GenAI Units per token than a less capable model.

When Are Tokens and GenAI Units Consumed?

Text generation resources consume both LLM input and output tokens, which are converted to GenAI Units using the model-specific exchange rate.

Embeddings resources only consume input tokens. This is because only the generated embedding vectors are returned and the generated output is not tokenized.

Knowledge base resources do not consume tokens directly. Uploading a document to a knowledge base connected to an embeddings resource consumes tokens in that embeddings resource.

Exporting Consumption Data

Click Export to export consumption data in CSV format. The export contains information about input tokens, output tokens, and dates. Days with no consumption are not exported.

Team

The Team page allows you to manage access to the Mendix Cloud GenAI resource. By default, internal members listed in this Overview have access to the resource in the GenAI resource portal and can create new keys or invite new users. You can add new users via the Add Member button and remove them using the Remove Member button next to their name in the overview.

Inviting External Members

You can invite members from outside your organization to access your GenAI resources by entering their email address in Add Member. This option is available only if your company admin has enabled external user invitations.

You can track invitations in the Pending Invites tab. Invited users receive an email with a link to accept or decline the invitation. If they do not yet have a Mendix account, the link redirects them to create one. Once the invitation is accepted, the resource appears in their GenAI portal overview.

You can withdraw pending invitations at any time. Invitations automatically expire after two weeks. External members can create and delete keys, export consumption data, manage knowledge base content and collections, and change the model. However, they cannot modify the display name or environment, or manage team membership.

Keys

The Keys tab allows you to manage configuration keys for the resources. These keys provide programmatic access to the GenAI resources. From the Keys tab, you can create new keys and revoke existing ones.

To create a new key, click Create Key, add a description, and save the changes. A dialog box displays the key.

Store it securely. The key is shown only once.

Once created, the key can be used in the Mendix application via the Mendix Cloud GenAI connector. A single key exposes all model versions currently enabled on the resource. When you import the key into your application, all available models are accessible. No key rotation is required when new model versions are added to the resource.

Additional Information for Knowledge Base Resource Keys

When you create a key for a knowledge base, an embeddings resource key is automatically generated for the selected embeddings model and marked accordingly in the keys overview. To configure a knowledge base connection from a Mendix application, you only need to import the knowledge base resource key. The connection details for the embeddings model are created automatically.

Content (Only for Knowledge Bases)

The Content tab is available only for Knowledge Bases.

On the Content page, you can find information on adding knowledge to your Knowledge Base resource and managing its content.

Currently, you have the following options for adding data to a Knowledge Base:

Add files (for example, TXT or PDF)
Add data from a Mendix application.

Add Files

When you select the Add Files Like .TXT or .PDF option, you can upload documents directly to the GenAI portal. Before uploading, you also have the option to add metadata. For more information, see the metadata section below.

Only TXT and PDF files are supported.

Before uploading, you can choose to upload the data to a new collection, the default collection, or another existing collection within the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on its shared domain, purpose, or thematic focus. Below is a diagram showing how resources are organized into separate collections. This approach allows multiple use cases to share a common resource while the option to only add the required collections to the conversation context is preserved.

While collections provide a mechanism for data separation, it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of Metadata.

Metadata

Metadata is additional information that can be attached to data in a GenAI knowledge base. Unlike the actual content, metadata provides structured details that help in organizing, searching, and filtering information more efficiently. It helps manage large datasets by allowing the retrieval of relevant data based on specific attributes rather than relying solely on similarity-based searches.

Metadata consists of key-value pairs and serves as additional information connected to the data, though it is not part of the vectorization itself.

In the employee onboarding and IT ticket support example, instead of having two different collections, such as IT setup, and equipment and historical support tickets, there could be one named 'Company IT'. To retrieve tickets only and no other information from this collection, add the metadata below during insertion.

key: Category, value: Ticket

The model then generates its response using the specified metadata instead of solely the input text.

Using metadata, even more fine-grained filtering becomes feasible. Each ticket may have associated metadata, such as

key: Ticket Type, value: Bug

key: Status, value: Solved

key: Priority, value: High

Instead of relying solely on similarity-based searches of ticket descriptions, users can then filter for specific tickets, such as 'Bug' tickets with the status set to 'Solved'.

Add Data from a Mendix Application

You can upload data directly from Mendix to the Knowledge Base. To do so, several operations of the Mendix Cloud GenAI connector are required. For a detailed guide on this process, see the Add Data Chunks to Your Knowledge Base section of Mendix Cloud GenAI Connector.

Settings

The Settings tab contains the details of a GenAI resource. It shows the following:

Display Name – The name of the resource.
ID – The resource ID.
Company – The company name.
Region(s) – The region where the resource is hosted.
Cross Region Inference (CRI) – Indicates whether cross region inference is enabled for this resource ¹.
Cloud Provider – The cloud provider, for example, AWS.
Type – The type of resource, for example, Text Generation Model, Embeddings Generation, or Knowledge Base.
Available Models – The model versions enabled on the resource. For text generation resources, this lists all Claude model versions available for use. For embeddings resources, this lists all available Cohere Embed model versions. For a full list of supported models, see Supported Models.
Default Model – The model version used as a fallback when no model is explicitly specified in an API call. This field only applies to text generation resources and is present for backward compatibility with apps using connector below V6.2.0.
Capacity – The monthly GenAI Unit allocation for the resource, for example, 1,000 GenAI Units.
Environment – The environment, for example, Test, Acceptance, or Production.

¹ Cross Region Inference (CRI) allows a model to redirect requests to another region, helping to distribute the load across multiple regions within the same area. EU requests always stay within EU regions. Connecting to a cross region inference profile does not change how the request is sent; the redirection happens on the server side, determining the region to handle the request to get the fastest response. For more information, see Increase throughput with cross-region inference. If applicable, CRI profiles are selected during provisioning of a model resource. New models are available under the CRI inferencing type by default.

Additional Details for Knowledge Base Resources

For knowledge base resources, you can also see details of the associated embeddings resource and vice versa. To learn more about embeddings, see the Embedding vector section of RAG in a Mendix App.

Adjusting the GenAI Unit Capacity of a Resource

After a resource is provisioned, you can change its GenAI Unit capacity to match your actual usage. Company Admins can adjust the capacity through the GenAI Resources self-service in the Control Center. For more information, see the Adjusting Resource GenAI Unit Capacity section of GenAI Resources.