Merge pull request #300709 from dlepow/apimgem

[APIM] Add Gemini LLM example

Author: AnnaMHuff

articles/api-management/TOC.yml

@@ -236,18 +236,22 @@
   items:
   - name: AI gateway capabilities in API Management
     href: genai-gateway-capabilities.md
-  - name: Import Azure AI Foundry API
-    href: azure-ai-foundry-api.md
-  - name: Import Azure OpenAI API
-    href: azure-openai-api-from-specification.md
-  - name: Import OpenAI-compatible LLM API
-    href: openai-compatible-llm-api.md
-  - name: Authenticate and authorize to Azure OpenAI
-    href: api-management-authenticate-authorize-azure-openai.md
+  - name: Import LLM APIs
+    items:
+    - name: Import Azure AI Foundry API
+      href: azure-ai-foundry-api.md
+    - name: Import Azure OpenAI API
+      href: azure-openai-api-from-specification.md
+    - name: Import language model API
+      href: openai-compatible-llm-api.md
+    - name: Import Google Gemini API
+      href: openai-compatible-google-gemini-api.md
   - name: Expose REST API as MCP server
     href: export-rest-mcp-server.md
   - name: Semantic caching for Azure OpenAI API requests
     href: azure-openai-enable-semantic-caching.md
+  - name: Authenticate and authorize to Azure OpenAI
+    href: api-management-authenticate-authorize-azure-openai.md
   - name: Protect Azure OpenAI keys
     href: /semantic-kernel/deploy/use-ai-apis-with-api-management?toc=%2Fazure%2Fapi-management%2Ftoc.json&bc=/azure/api-management/breadcrumb/toc.json
 - name: Manage APIs with policies
@@ -689,4 +693,4 @@
   - name: Stack Overflow
     href: https://stackoverflow.com/questions/tagged/azure-api-management
   - name: aka.ms/apimlove
-    href: https://aka.ms/apimlove
+    href: https://aka.ms/apimlove

articles/api-management/media/openai-compatible-google-gemini-api/gemini-import.png

@@ -0,0 +1,92 @@
+---
+title: Import OpenAI-Compatible Google Gemini API - Azure API Management
+description: How to import an OpenAI-compatible Google Gemini model as a REST API in Azure API Management and manage a chat completions endpoint
+ms.service: azure-api-management
+author: dlepow
+ms.author: danlep
+ms.topic: how-to
+ms.date: 07/06/2025
+ms.collection: ce-skilling-ai-copilot
+ms.custom: template-how-to
+---
+
+# Import an OpenAI-compatible Google Gemini API
+
+[!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
+
+This article shows you how to import an OpenAI-compatible Google Gemini API to access models such as `gemini-2.0-flash`. For these models, Azure API Management can manage an OpenAI-compatible chat completions endpoint.
+
+Learn more about managing AI APIs in API Management:
+
+* [AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)
+* [Import a language model API](openai-compatible-llm-api.md)
+
+## Prerequisites
+
+- An existing API Management instance. [Create one if you haven't already](get-started-create-service-instance.md).
+- An API key for the Gemini API. If you don't have one, create it at [Google AI Studio](https://aistudio.google.com/apikey) and store it in a safe location.
+
+
+## Import an OpenAI-compatible Gemini API using the portal
+
+1. In the [Azure portal](https://portal.azure.com), navigate to your API Management instance.
+1. In the left menu, under **APIs**, select **APIs** > **+ Add API**.
+1. Under **Define a new API**, select **Language Model API**.
+    
+    :::image type="content" source="media/openai-compatible-llm-api/openai-api.png" alt-text="Screenshot of creating a passthrough language model API in the portal." :::
+1. On the **Configure API** tab:
+    1. Enter a **Display name** and optional **Description** for the API.
+    1. In **URL**, enter the following base URL from the [Gemini OpenAI compatibility documentation](https://ai.google.dev/gemini-api/docs/openai):
+         `https://generativelanguage.googleapis.com/v1beta/openai`
+
+    1. In **Path**, append a path that your API Management instance uses to route requests to the Gemini API endpoints.
+    1. In **Type**, select **Create OpenAI API**.
+    1. In **Access key**, enter the following:
+        1. **Header name**: *Authorization*.
+        1. **Header value (key)**: `Bearer` followed by your API key for the Gemini API.
+    
+    :::image type="content" source="media/openai-compatible-google-gemini-api/gemini-import.png" alt-text="Screenshot of importing a Gemini LLM API in the portal.":::
+
+1. On the remaining tabs, optionally configure policies to manage token consumption, semantic caching, and AI content safety. For details, see [Import a language model API](openai-compatible-llm-api.md).
+1. Select **Review**.
+1. After settings are validated, select **Create**.
+
+API Management creates the API and configures the following:
+
+* A [backend](backends.md) resource and a [set-backend-service](set-backend-service-policy.md) policy that direct API requests to the Google Gemini endpoint.
+*  Access to the LLM backend using the Gemini API key you provided. The key is protected as a secret [named value](api-management-howto-properties.md) in API Management.
+* (optionally) Policies to help you monitor and manage the API.
+
+### Test Gemini model
+
+After importing the API, you can test the chat completions endpoint for the API.
+
+1. Select the API that you created in the previous step.
+1. Select the **Test** tab.
+1. Select the `POST  Creates a model response for the given chat conversation` operation, which is a `POST` request to the `/chat/completions` endpoint.
+1. In the **Request body** section, enter the following JSON to specify the model and an example prompt. In this example, the `gemini-2.0-flash` model is used.
+
+    ```json
+    {
+        "model": "gemini-2.0-flash",
+        "messages": [
+            {
+                "role": "system",
+                "content": "You are a helpful assistant"
+            },
+            {
+                "role": "user",
+                "content": "How are you?"
+            }
+        ],
+        "max_tokens": 50
+    }
+    ```
+    
+    When the test is successful, the backend responds with a successful HTTP response code and some data. Appended to the response is token usage data to help you monitor and manage your language model token consumption.
+
+    :::image type="content" source="media/openai-compatible-google-gemini-api/gemini-test.png" alt-text="Screenshot of testing a Gemini LLM API in the portal.":::
+
+## Related content
+
+* [AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)

articles/api-management/media/openai-compatible-google-gemini-api/gemini-test.png

@@ -1,33 +1,33 @@
 ---
-title: Import OpenAI-Compatible Language Model API - Azure API Management
-description: How to import an OpenAI-compatible language model or a non-Azure-provided AI model as a REST API in Azure API Management.
+title: Import Language Model API - Azure API Management
+description: How to import an OpenAI-compatible language model or a non-OpenAI-compatible AI model as a REST API in Azure API Management.
 ms.service: azure-api-management
 author: dlepow
 ms.author: danlep
 ms.topic: how-to
-ms.date: 05/15/2025
+ms.date: 07/06/2025
 ms.update-cycle: 180-days
 ms.collection: ce-skilling-ai-copilot
-ms.custom: template-how-to, build-2024
+ms.custom: template-how-to
 ---
 
-# Import an OpenAI-compatible language model API 
+# Import a language model API 
 
 [!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
 
-You can import OpenAI-compatible language model endpoints to your API Management instance as APIs. For example, you might want to manage an LLM that you self-host, or that's hosted on an inference provider other than Azure AI services. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
+You can import OpenAI-compatible language model endpoints to your API Management instance as APIs. You can also import language models that aren't compatible with OpenAI as passthrough APIs, which forward requests directly to the backend endpoints. For example, you might want to manage an LLM that you self-host, or that's hosted on an inference provider other than Azure AI services. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
 
 Learn more about managing AI APIs in API Management:
 
-* [Generative AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)
+* [AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)
 
 ## Language model API types
 
 API Management supports two types of language model APIs for this scenario. Choose the option suitable for your model deployment. The option determines how clients call the API and how the API Management instance routes requests to the AI service.
 
-* **OpenAI-compatible** - Language model endpoints that are compatible with OpenAI's API. Examples include certain models exposed by inference providers such as [Hugging Face Text Generation Inference (TGI)](https://huggingface.co/docs/text-generation-inference/en/index).
+* **OpenAI-compatible** - Language model endpoints that are compatible with OpenAI's API. Examples include certain models exposed by inference providers such as [Hugging Face Text Generation Inference (TGI)](https://huggingface.co/docs/text-generation-inference/en/index) and [Google Gemini API](openai-compatible-google-gemini-api.md).
 
-    API Management configures an OpenAI-compatible chat completions endpoint. 
+    For an OpenAI-compatible LLM, API Management configures a chat completions endpoint. 
 
 * **Passthrough** - Other language model endpoints that aren't compatible with OpenAI's API. Examples include models deployed in [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html) or other providers.
 
@@ -41,6 +41,11 @@ API Management supports two types of language model APIs for this scenario. Choo
 
 ## Import language model API using the portal
 
+When you import the LLM API in the portal, API Management automatically configures:
+
+* A [backend](backends.md) resource and a [set-backend-service](set-backend-service-policy.md) policy that direct API requests to the LLM endpoint.
+* (optionally) Access to the LLM backend using an access key you provide. The key is protected as a secret [named value](api-management-howto-properties.md) in API Management.
+* (optionally) Policies to help you monitor and manage the API.
 
 To import a language model API to API Management:
 
@@ -71,6 +76,8 @@ To import a language model API to API Management:
 1. Select **Review**.
 1. After settings are validated, select **Create**. 
 
+API Management creates the API, and configures operations for the LLM endpoints. By default, the API requires an API Management subscription.
+
 ## Test the LLM API
 
 To ensure that your LLM API is working as expected, test it in the API Management test console. 
@@ -85,5 +92,6 @@ To ensure that your LLM API is working as expected, test it in the API Managemen
 
     When the test is successful, the backend responds with a successful HTTP response code and some data. Appended to the response is token usage data to help you monitor and manage your language model token consumption.
 
+## Related content
 
-[!INCLUDE [api-management-define-api-topics.md](../../includes/api-management-define-api-topics.md)]
+* [AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)