SAP AI Core

SAP AI Core and the generative AI hub help you to integrate LLMs and AI into new business processes in a cost-efficient manner.

Website: SAP Help Portal

<Info> SAP AI Core, and Generative AI Hub, are offerings from SAP BTP. You need an active SAP BTP contract and a existing subaccount with a SAP AI Core instance with the `extended` service plan (For more details about SAP AI Core service plans and their capabilities, see the [Service Plans documentation](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/service-plans)) to perform these steps. </Info>

Getting a Service Binding

1. Access: Go to your subaccount via BTP Cloud Cockpit
2. Create a Service Binding: Go to "Instances and Subscriptions", select your SAP AI Core service instance and click on Service Bindings > Create.
3. Copy the Service Binding: Copy the service binding values.

Supported Models

SAP AI Core supports a large and growing number of models. Refer to the Generative AI Hub Supported Models page for the complete and up-to-date list.

Configuration in Cline

1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
2. Select Provider: Choose "SAP AI Core" from the "API Provider" dropdown.
3. Enter Client Id: Add the .clientid field from the service binding into the "AI Core Client Id" field.
4. Enter Client Secret: Add the .clientsecret field from the service binding into the "AI Core Client Secret" field.
5. Enter Base URL: Add the .serviceurls.AI_API_URL field from the service binding into the "AI Core Base URL" field.
6. Enter Auth URL: Add the .url field from the service binding into the "AI Core Auth URL" field.
7. Enter Resource Group: Add the resource group where you have your model deployments. See Create a Deployment for a Generative AI Model.
8. Configure Orchestration Mode: If you have an extended service plan, the "Orchestration Mode" checkbox will automatically appear.
9. Select Model: Choose your desired model from the "Model" dropdown.

Orchestration Mode vs Native API

Orchestration Mode:

• Simplified usage: Provides access to all available models without requiring individual deployments using the Harmonized API

Native API Mode:

• Manual deployments: Requires manual model deployment and management in your SAP AI Core service instance

Tips and Notes

• Service Plan Requirement: You must have the SAP AI Core extended service plan to use LLMs with Cline. Other service plans do not provide access to Generative AI Hub.

• Orchestration Mode (Recommended): Keep Orchestration Mode enabled for the simplest setup. It provides automatic access to all available models without requiring manual deployments.

• Native API Mode: Only disable Orchestration Mode if you have specific requirements that necessitate direct AI Core API access or need features not supported by the orchestration mode.

• When using Native API Mode:

  • Model Selection: The model dropdown displays models in two separate lists:
    • Deployed Models: These models are already deployed in your specified resource group and are ready to use immediately.
    • Not Deployed Models: These models don't have active deployments in your specified resource group. You won't be able to use these models until you create deployments for them in SAP AI Core.
  • Creating Deployments: To use a model that has not been deployed yet, you'll need to create a deployment in your SAP AI Core service instance. See Create a Deployment for a Generative AI Model for instructions.

Configuring Reasoning Effort for OpenAI Models

When using OpenAI reasoning models (such as o1, o3, o3-mini, o4-mini) through SAP AI Core, you can control the reasoning effort to balance performance and cost:

1. Open Cline Settings: Click the settings icon (⚙️) in the Cline panel.
2. Navigate to Features: Go to the "Features" section in the settings.
3. Find OpenAI Reasoning Effort: Locate the "OpenAI Reasoning Effort" setting.
4. Choose Effort Level: Select between:
   • Low: Faster responses with lower token usage, suitable for simpler tasks
   • Medium: Balanced performance and token usage for most tasks
   • High: More thorough analysis with higher token usage, better for complex reasoning tasks

<Note> This setting only applies when using OpenAI reasoning models (o1, o3, o3-mini, o4-mini, gpt-5, etc.) deployed through SAP AI Core. Other models will ignore this setting. </Note>