How to add your own models

Follow this setup guide to add your own AI models to your workspace.
How to add your own models

Follow this setup guide to add your own AI models to your workspace.
Prerequisites

Make sure that before you start configuring a model, you have ensured these prerequisites to setting up your BYOK workspace:
You have configured the model of your choice in your provider
You have configured the respective model key in your provider
How to add custom models to your workspace

Odeus comes with prebuilt configurations for the most popular AI models. You can pick from this catalog and we fill in all the provider settings automatically. All you need to do is provide your model credentials, and we handle the rest.
Prebuilt configurations are available for the most popular completion, image generation, and embedding models.
### 1. Select the model

Navigate to [Workspace Settings -> Models](https://app.odeus.ai/settings/workspace/models) and click **Add custom model**.

Select a completion model from the catalog. When you choose a pre-configured model, Odeus keeps all settings up to date. Pricing, context windows, and capabilities always reflect the latest from your provider.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/completions_choose_model_from_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=3801903eacce53c66259b514232f1f4c" alt="Choose model from configurations" style={{borderRadius: '6px'}} width="2064" height="1026" data-path="images/completions_choose_model_from_configuration.png" /&gt;

If your model isn't in the catalog, you can **Set up your model manually**.

***

### 2. Configure your model

If you selected a pre-configured model, Odeus has already filled in the technical settings. You only need to decide how to make it available in your workspace. If you chose manual setup, you'll configure everything yourself, from provider details to pricing and capabilities.

**Open the section below that matches your setup.**


  Odeus handles all the technical settings for you. The only decisions left are how you want to roll the model out to your workspace.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/completions_select_preconfigured_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=8b0021b73e4aac52ad4131e6dd085c0b" alt="Select a pre-configured model" style={{borderRadius: '6px'}} width="1070" height="708" data-path="images/completions_select_preconfigured_model.png" /&gt;

  * Set the model to invisible while you test it. Make it visible once you're satisfied with how it responds.
  * Decide whether the model should be available when building assistants.
  * Mark it as a premium model if you don't want users setting it as their personal default.
  * Use maintenance mode to pause usage without removing the model.


If you chose to set up the model manually, you now need to configure the technical parameters yourself. This includes general model info, connection settings, pricing, and capability flags that Odeus would otherwise manage for you.


  Setting up a model manually gives you full control over every configuration parameter. Keep in mind that you are responsible for keeping these settings accurate. Odeus won't automatically update things like context window size or pricing when a provider makes changes.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/completions_select_manual-setup_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=6334ba7edc7ac863f62be212adb193b6" alt="Set up a model manually" style={{borderRadius: '6px'}} width="1798" height="764" data-path="images/completions_select_manual-setup_model.png" /&gt;

  **General**

  * **Provider**: the organization that built the model (e.g. OpenAI, Anthropic).
  * **Provider model name**: the model identifier used by your provider.
  * **Region**: where the model is hosted. Shown to users as EU, US, or Global.
  * **Description (EN / DE)**: optional, max 150 characters each.

  **Configure**

  * **Context window size**: the model's context window in tokens.
  * **Max output tokens**: maximum tokens the model can generate per response.

  **Pricing**
  > Token prices are used for usage tracking and cost reporting.

  * **Input token price** (USD / 1M tokens)
  * **Output token price** (USD / 1M tokens)
  * **Cache read token price** (USD / 1M tokens)
  * **Cache write token price** (USD / 1M tokens)

  **Capabilities**

  * **Image analysis**: enable if the model supports image analysis.
  * **Canvas**: enable to allow the model to create documents using the canvas tool.
  * **Supports tools**: enable if the model supports tool calling.
  * **Supports temperature**: if disabled, the temperature parameter will not be sent to the model.
  * **Always show reasoning**: for models that natively produce reasoning output (e.g. o3, o4 Mini).
  * **Use Responses API**: use OpenAI's Responses API instead of Chat Completions.


***

### 3. Configure your deployment

A deployment connects your model to a specific provider endpoint using a model key. Select a key you have already configured in [Model Keys](/en/admin/byok/byok-setup#1-4-completion-models), or add a new one.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/completions_model_deployment_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=0c92aee028c07c64048a4dec65859743" alt="Model deployment configuration" style={{borderRadius: '6px'}} width="2782" height="1396" data-path="images/completions_model_deployment_configuration.png" /&gt;

* **Key**: select an existing model key or add a new one.
* **Model identifier**: the deployment name or model ID as defined in your provider's configuration.
* **Tokens per minute (TPM)**: optional. Limit how many tokens per minute can be processed through this deployment.

> Add fallback models to improve availability or manage provider limits. See [How to add fallback models](/en/admin/byok/fallback-models).

***

### 4. Review your model

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/completions_review_model_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=9b034891e20977e2b1d6466cb6ca5705" alt="Review model configuration before saving" style={{borderRadius: '6px'}} width="1538" height="910" data-path="images/completions_review_model_configuration.png" /&gt;

Once you have tested the model successfully, review the final settings before saving and making it available to your workspace.

You have now added your own completion model to Odeus 🎉



### 1. Select the model

Navigate to [Workspace Settings -> Models](https://app.odeus.ai/settings/workspace/models) and click **Add custom model**.

Select an image generation model from the catalog. When you choose a pre-configured model, Odeus keeps all settings up to date. Pricing, context windows, and capabilities always reflect the latest from your provider.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/image_choose_model_from_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=8d1c78cc7155503c29bd664f9e3049a3" alt="Choose image model from configurations" style={{borderRadius: '6px'}} width="2004" height="1038" data-path="images/image_choose_model_from_configuration.png" /&gt;

If your model isn't in the catalog, you can **Set up your model manually**.

***

### 2. Configure your model

If you selected a pre-configured model, Odeus has already filled in the technical settings. You only need to decide how to make it available in your workspace. If you chose manual setup, you'll configure everything yourself, from provider details to pricing and capabilities.

**Open the section below that matches your setup.**


  Odeus handles all the technical settings for you. You only need to set the region and decide how the model is available in your workspace.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/image_select_preconfigured_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=2bf002cfdf93d6543589df47bdb33b02" alt="Select a pre-configured image model" style={{borderRadius: '6px'}} width="2046" height="1348" data-path="images/image_select_preconfigured_model.png" /&gt;

  * **Region**: select where the model is hosted (EU, US, or Global). This is shown to users so they know where their data is processed.
  * **Visible to users**: when enabled, this model will be available for users in the workspace. Keep it off while you test it.
  * **Max images per user**: optional. Set a limit on how many images a user can generate within a time window (e.g. 50 per 3 hours).


If you chose to set up the model manually, you now need to configure the technical parameters yourself. This includes general model info, description, usage limits, and capability flags that Odeus would otherwise manage for you.


  Setting up a model manually gives you full control over every configuration parameter. Keep in mind that you are responsible for keeping these settings accurate. Odeus won't automatically update them when a provider makes changes.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/image_select_manual-setup_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=0e8ea7038e9f34e48816c259c58c6524" alt="Set up an image model manually" style={{borderRadius: '6px'}} width="1890" height="852" data-path="images/image_select_manual-setup_model.png" /&gt;

  **General**

  * **Model name**: the display name shown to users.
  * **Provider model name**: the model identifier used by your provider.
  * **Provider**: the organization that built the model (e.g. OpenAI, Google).
  * **Region**: where the model is hosted. Shown to users as EU, US, or Global.

  **Visibility**

  * **Visible to users**: when enabled, this model will be available for users in the workspace.

  **Description**

  * **Description (EN)**: optional, max 150 characters.
  * **Description (DE)**: optional, max 150 characters.

  **Configure**

  * **Max images per user**: optional. Set a limit on how many images a user can generate within a time window (e.g. 50 per 3 hours).

  **Advanced**

  * **Image generation**: all image models can generate images by default.
  * **Image editing**: enable if the model supports editing existing images.


***

### 3. Configure your deployment

A deployment connects your model to a specific provider endpoint using a model key. Select a key you have already configured in [Model Keys](/en/admin/byok/byok-setup#1-4-completion-models), or add a new one.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/image_model_deployment_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=1b1de23b02e8f5edac3f0e6f4e61ae4b" alt="Image model deployment configuration" style={{borderRadius: '6px'}} width="2138" height="1002" data-path="images/image_model_deployment_configuration.png" /&gt;

* **Key**: select an existing model key or add a new one.
* **Model identifier**: the deployment name or model ID as defined in your provider's configuration.
* **Tokens per minute (TPM)**: optional. Limit how many tokens per minute can be processed through this deployment.

> Add fallback models to improve availability or manage provider limits. See [How to add fallback models](/en/admin/byok/fallback-models).

***

### 4. Review your model

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/image_review_model_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=f3aff70fd12ac80e67aa32ed01316a96" alt="Review image model configuration before saving" style={{borderRadius: '6px'}} width="1940" height="1256" data-path="images/image_review_model_configuration.png" /&gt;

Once you have tested the model successfully, review the final settings before saving and making it available to your workspace.

You have now added your own image generation model to Odeus 🎉



### 1. Select the model

Navigate to [Workspace Settings -> Models](https://app.odeus.ai/settings/workspace/models) and click **Add custom model**.

Select an embedding model from the catalog. When you choose a pre-configured model, Odeus keeps all settings up to date. Pricing, context windows, and capabilities always reflect the latest from your provider.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/embedding_choose_model_from_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=527831bb3d93282ef58b7e714df02d41" alt="Choose embedding model from configurations" style={{borderRadius: '6px'}} width="2098" height="932" data-path="images/embedding_choose_model_from_configuration.png" /&gt;

If your model isn't in the catalog, you can **Set up your model manually**.

***

### 2. Configure your model

If you selected a pre-configured model, Odeus has already filled in the technical settings. You only need to decide how to make it available in your workspace. If you chose manual setup, you'll configure everything yourself, from provider details to pricing and capabilities.

**Open the section below that matches your setup.**


  Odeus handles all the technical settings for you. The only decision left is whether to make the model available to users.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/embedding_select_preconfigured_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=da6d9a9a9080186491355b7e99b08b99" alt="Select a pre-configured embedding model" style={{borderRadius: '6px'}} width="1466" height="714" data-path="images/embedding_select_preconfigured_model.png" /&gt;

  * **Visible to users**: when enabled, this model will be available for users in the workspace. Keep it off while you test it.


If you chose to set up the model manually, you now need to configure the technical parameters yourself. This includes general model info, connection settings, and capability flags that Odeus would otherwise manage for you.


  Setting up a model manually gives you full control over every configuration parameter. Keep in mind that you are responsible for keeping these settings accurate. Odeus won't automatically update them when a provider makes changes.

  &lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/embedding_select_manual-setup_model.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=d0c1c0ab337b549cfbd0d260b8dd12f4" alt="Set up an embedding model manually" style={{borderRadius: '6px'}} width="2468" height="1030" data-path="images/embedding_select_manual-setup_model.png" /&gt;

  **Visibility**

  * **Visible to users**: when enabled, this model will be available for users in the workspace.

  **Configure**

  * **Vector Similarity Threshold**: minimum similarity score (0.1–1) required for embedding matches. Higher values return more relevant but fewer results. Defaults to 0.5.


***

### 3. Configure your deployment

A deployment connects your model to a specific provider endpoint using a model key. Select a key you have already configured in [Model Keys](/en/admin/byok/byok-setup#1-4-completion-models), or add a new one.

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/embedding_model_deployment_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=761ac042715a8c91cf07dd42ce8c9b9b" alt="Embedding model deployment configuration" style={{borderRadius: '6px'}} width="2244" height="1076" data-path="images/embedding_model_deployment_configuration.png" /&gt;

* **Key**: select an existing model key or add a new one.
* **Model identifier**: the deployment name or model ID as defined in your provider's configuration.

> Add fallback models to improve availability or manage provider limits. See [How to add fallback models](/en/admin/byok/fallback-models).

***

### 4. Review your model

&lt;img src="https://mintcdn.com/odeus-34/_Ql2nLzRgbjA7kny/images/embedding_review_model_configuration.png?fit=max&auto=format&n=_Ql2nLzRgbjA7kny&q=85&s=09a04e2e591c9d70a62a1bafeb103608" alt="Review embedding model configuration before saving" style={{borderRadius: '6px'}} width="2036" height="1338" data-path="images/embedding_review_model_configuration.png" /&gt;

Once you have tested the model successfully, review the final settings before saving and making it available to your workspace.

You have now added your own embedding model to Odeus 🎉