Skip to content

Commit 2da3f94

Browse files
committed
edits
1 parent eba767b commit 2da3f94

File tree

4 files changed

+27
-31
lines changed

4 files changed

+27
-31
lines changed

articles/api-management/TOC.yml

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -208,8 +208,12 @@
208208
items:
209209
- name: AI gateway capabilities in API Management
210210
href: genai-gateway-capabilities.md
211+
- name: Import Azure AI Foundry API
212+
href: azure-ai-foundry-api.md
211213
- name: Import Azure OpenAI API
212214
href: azure-openai-api-from-specification.md
215+
- name: Import OpenAI-compatible LLM API
216+
href: openai-compatible-llm-api.md
213217
- name: Import LLM API
214218
href: openai-compatible-llm-api.md
215219
- name: Authenticate and authorize to Azure OpenAI

articles/api-management/azure-ai-foundry-api.md

Lines changed: 11 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ ms.custom: template-how-to, build-2024
1414

1515
[!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
1616

17-
You can import AI model endpoints deployed in Azure AI Foundry to your API Management instance as a REST API. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
17+
You can import AI model endpoints deployed in Azure AI Foundry to your API Management instance. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
1818

1919
Learn more about managing AI APIs in API Management:
2020

@@ -23,29 +23,25 @@ Learn more about managing AI APIs in API Management:
2323

2424
## Client compatibility options
2525

26-
API Management supports two client compatibility options for AI APIs. The option you select determines how clients call the API and how the API Management instance routes requests to the AI service.
26+
API Management supports two client compatibility options for AI APIs. 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.
2727

2828
* **Azure AI** - Manage model endpoints in Azure AI Foundry that are exposed through the [Azure AI Model Inference API](/azure/ai-studio/reference/reference-model-inference-api).
2929

30-
Clients call the deployment at a `/models` endpoint such as `/Deepseek-3/models/chat/completions`. Deployment name is passed in the request body. Use this option if your service includes models exposed through the Azure AI Model Inference API.
30+
Clients call the deployment at a `/models` endpoint such as `/my-model/models/chat/completions`. Deployment name is passed in the request body. Use this option if your AI service includes models exposed through the Azure AI Model Inference API.
3131

3232
* **Azure OpenAI Service** - Manage model endpoints deployed in Azure OpenAI Service.
3333

34-
Clients call the deployment at an `/openai` endpoint such as `/openai/deployments/my-deployment/chat/completions`. Deployment name is passed in the request path. Use this option if your service only includes Azure OpenAI Service model deployments.
34+
Clients call the deployment at an `/openai` endpoint such as `/openai/deployments/my-deployment/chat/completions`. Deployment name is passed in the request path. Use this option if your AI service only includes Azure OpenAI Service model deployments.
3535

3636
## Prerequisites
3737

3838
- An existing API Management instance. [Create one if you haven't already](get-started-create-service-instance.md).
39-
- One or more Azure AI services with models deployed, such as:
40-
4139
- An Azure AI service in your subscription with one or more models deployed. Examples include models deployed in Azure AI Foundry or Azure OpenAI Service.
4240

43-
## Import AI API using the portal
41+
## Import AI Foundry API using the portal
4442

4543
Use the following steps to import an AI API to API Management.
4644

47-
[!INCLUDE [api-management-workspace-availability](../../includes/api-management-workspace-availability.md)]
48-
4945
When you import the API, API Management automatically configures:
5046

5147
* Operations for each of the API's REST API endpoints
@@ -68,11 +64,11 @@ To import an AI Foundry API to API Management:
6864
1. Select **Next**.
6965
1. On the **Configure API** tab:
7066
1. Enter a **Display name** and optional **Description** for the API.
71-
1. In **Path**, enter a path that your API Management instance uses to access the deployment endpoint.
67+
1. In **Base path**, enter a path that your API Management instance uses to access the deployment endpoint.
7268
1. Optionally select one or more **Products** to associate with the API.
73-
1. In **Client compatibility**, select either of the following based on the types of client you intend to support. See [AI service options](#ai-service-options) for more information.
74-
* **Azure OpenAI** - Select this option if your deployment only includes Azure OpenAI Service model deployments.
75-
* **Azure AI** - Select this option if your deployment includes other models available through Azure AI Foundry.
69+
1. In **Client compatibility**, select either of the following based on the types of client you intend to support. See [Client compatibility options](#client-compatibility-options) for more information.
70+
* **Azure OpenAI** - Select this option if your clients only need to access Azure OpenAI Service model deployments.
71+
* **Azure AI** - Select this option if your clients need to access other model in Azure AI Foundry.
7672
1. Select **Next**.
7773

7874
:::image type="content" source="media/azure-ai-foundry-api/client-compatibility.png" alt-text="Screenshot of AI Foundry API configuration in the portal.":::
@@ -82,7 +78,7 @@ To import an AI Foundry API to API Management:
8278
* [Track token usage](llm-emit-token-metric-policy.md)
8379
1. On the **Apply semantic caching** tab, optionally enter settings or accept defaults that define the policies to help optimize performance and reduce latency for the API:
8480
* [Enable semantic caching of responses](azure-openai-enable-semantic-caching.md)
85-
On the **AI content safety**, optionally enter settings or accept defaults to configure the Azure AI Content Safety service checks for API requests:
81+
1. On the **AI content safety**, optionally enter settings or accept defaults to configure the Azure AI Content Safety service checks for API requests:
8682
* [Enforce content safety checks on LLM requests](llm-content-safety-policy.md)
8783
1. Select **Review**.
8884
1. After settings are validated, select **Create**.
@@ -92,7 +88,7 @@ On the **AI content safety**, optionally enter settings or accept defaults to co
9288
To ensure that your AI API is working as expected, test it in the API Management test console.
9389
1. Select the API you created in the previous step.
9490
1. Select the **Test** tab.
95-
1. Select an operation that's compatible with the model in the lanaguage API.
91+
1. Select an operation that's compatible with the model deployment.
9692
The page displays fields for parameters and headers.
9793
1. Enter parameters and headers as needed. Depending on the operation, you might need to configure or update a **Request body**.
9894
> [!NOTE]

articles/api-management/openai-compatible-llm-api.md

Lines changed: 8 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
---
2-
title: Import a Language Model API as REST API - Azure API Management
3-
description: How to import an OpenAI-compatible language model API or other AI model as a REST API in Azure API Management.
2+
title: Import a Self-Hosted Language Model API - Azure API Management
3+
description: How to import a self-hosted OpenAI-compatible language model or other AI model as a REST API in Azure API Management.
44
ms.service: azure-api-management
55
author: dlepow
66
ms.author: danlep
@@ -10,23 +10,23 @@ ms.collection: ce-skilling-ai-copilot
1010
ms.custom: template-how-to, build-2024
1111
---
1212

13-
# Import a language model API
13+
# Import a self-hosted language model API
1414

1515
[!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
1616

17-
You can import AI model endpoints deployed outside Azure to your API Management instance as a REST API. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
17+
You can import self-hosted AI model endpoints to your API Management instance. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
1818

1919
Learn more about managing AI APIs in API Management:
2020

2121
* [Generative AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)
2222

2323
## Language model API types
2424

25-
API Management supports two types of self-hosted language model APIs. The option you select determines how clients call the API and how the API Management instance routes requests to the AI service.
25+
API Management supports two types of self-hosted language model APIs. 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.
2626

27-
* **OpenAI-compatible** - Self-hosted model endpoints that are compatible with OpenAI's API. Examples include models exposed by inference providers such as [Hugging Face Text Generation Inference (TGI)](https://huggingface.co/docs/text-generation-inference/en/index).
27+
* **OpenAI-compatible** - Self-hosted 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).
2828

29-
API Management configures an OpenAI-compatible chat completions endpoint. Clients call the deployment at an `/openai` endpoint such as `/openai/deployments/my-deployment/chat/completions`.
29+
API Management configures an OpenAI-compatible chat completions endpoint.
3030

3131
* **Passthrough** - Other self-hosted 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.
3232

@@ -42,8 +42,6 @@ API Management supports two types of self-hosted language model APIs. The option
4242

4343
Use the following steps to import a language model API to API Management.
4444

45-
[!INCLUDE [api-management-workspace-availability](../../includes/api-management-workspace-availability.md)]
46-
4745
To import a language model API to API Management:
4846

4947
1. In the [Azure portal](https://portal.azure.com), navigate to your API Management instance.
@@ -78,7 +76,7 @@ To import a language model API to API Management:
7876
To ensure that your LLM API is working as expected, test it in the API Management test console.
7977
1. Select the API you created in the previous step.
8078
1. Select the **Test** tab.
81-
1. Select an operation that's compatible with the model in the LLM API.
79+
1. Select an operation that's compatible with the model deployment.
8280
The page displays fields for parameters and headers.
8381
1. Enter parameters and headers as needed. Depending on the operation, you might need to configure or update a **Request body**.
8482
> [!NOTE]

includes/api-management-azure-openai-models.md

Lines changed: 4 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -14,15 +14,13 @@ The policy is used with APIs [added to API Management from the Azure OpenAI Serv
1414

1515
| API type | Supported models |
1616
|-------|-------------|
17-
| Chat completion | `gpt-3.5`<br/><br/>`gpt-4`<br/><br/>`gpt-4o`<sup>1</sup><br/><br/>`gpt-4o-mini`<sup>1</sup><br/><br/>`o1`<br/><br/>`03` |
18-
| Embeddings | `text-embedding-3-large`<br/><br/> `text-embedding-3-small`<sup>1</sup><br/><br/>`text-embedding-ada-002` |
19-
| Responses (preview) | `gpt-4o` (Versions: `2024-11-20`, `2024-08-06`, `2024-05-13`)<br/><br/>`gpt-4o-mini`<sup>1</sup> (Version: `2024-07-18`)<br/><br/>`gpt-4.1` (Version: `2025-04-14`)<br/><br/>`gpt-4.1-nano` (Version: `2025-04-14`)<br/><br/>`gpt-4.1-mini` (Version: `2025-04-14`)<br/><br/>`gpt-image-1` (Version: `2025-04-15`)<br/><br/>`o3` (Version: `2025-04-16`)<br/><br/>`o4-mini` (Version: `2025-04-16)
17+
| Chat completion | `gpt-3.5`<br/><br/>`gpt-4`<br/><br/>`gpt-4o`<br/><br/>`gpt-4o-mini`<br/><br/>`o1`<br/><br/>`o3` |
18+
| Embeddings | `text-embedding-3-large`<br/><br/> `text-embedding-3-small`<br/><br/>`text-embedding-ada-002` |
19+
| Responses | `gpt-4o` (Versions: `2024-11-20`, `2024-08-06`, `2024-05-13`)<br/><br/>`gpt-4o-mini` (Version: `2024-07-18`)<br/><br/>`gpt-4.1` (Version: `2025-04-14`)<br/><br/>`gpt-4.1-nano` (Version: `2025-04-14`)<br/><br/>`gpt-4.1-mini` (Version: `2025-04-14`)<br/><br/>`gpt-image-1` (Version: `2025-04-15`)<br/><br/>`o3` (Version: `2025-04-16`)<br/><br/>`o4-mini` (Version: `2025-04-16)
2020

2121

22-
<sup>1</sup> Model is multimodal (accepts text or image inputs and generates text).
23-
2422
> [!NOTE]
2523
> Traditional completion APIs are only available with legacy model versions and support is limited.
2624
27-
For more information, see [Azure OpenAI Service models](/azure/ai-services/openai/concepts/models).
25+
For current information about the models and their capabilities, see [Azure OpenAI Service models](/azure/ai-services/openai/concepts/models).
2826

0 commit comments

Comments
 (0)