Merge pull request #7548 from MicrosoftDocs/main

Auto Publish – main to live - 2025-10-08 17:04 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/openai/concepts/default-safety-policies.md

@@ -53,7 +53,7 @@ Text models in the Azure OpenAI can take in and generate both text and code. The
 
 ### Image generation models
 
-#### [GPT-image-1](#tab/gpt-image-1)
+#### [GPT-image-1 series](#tab/gpt-image-1)
 
 | Risk Category   | Prompt/Completion | Severity Threshold |
 |---------------------------------------------------|------------------------|---------------------|

articles/ai-foundry/openai/how-to/content-filters.md

@@ -26,7 +26,7 @@ Prompt shields and protected text and code models are optional and on by default
 > All customers have the ability to modify the content filters and configure the severity thresholds (low, medium, high). Approval is required for turning the content filters partially or fully off. Managed customers only may apply for full content filtering control via this form: [Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). At this time, it is not possible to become a managed customer.
 
 > [!IMPORTANT]
-> The GPT-image-1 model does not support content filtering configuration: only the default content filter is used.
+> The GPT-image-1 series models do not support content filtering configuration: only the default content filter is used.
 
 Content filters can be configured at the resource level. Once a new configuration is created, it can be associated with one or more deployments. For more information about model deployment, see the [resource deployment guide](create-resource.md).
 

articles/ai-foundry/openai/how-to/dall-e.md

@@ -24,8 +24,24 @@ OpenAI's image generation models create images from user-provided text prompts a
 
 - An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services).
 - An Azure OpenAI resource created in a supported region. See [Region availability](/azure/ai-foundry/openai/concepts/models#model-summary-table-and-region-availability).
-- Deploy a `dall-e-3` or `gpt-image-1` model with your Azure OpenAI resource. For more information on deployments, see [Create a resource and deploy a model with Azure OpenAI](/azure/ai-foundry/openai/how-to/create-resource).
-    - GPT-image-1 is the newer model and features a number of improvements over DALL-E 3. It's available in limited access: apply for access with [this form](https://aka.ms/oai/gptimage1access).
+- Deploy a `dall-e-3` or `gpt-image-1` series model with your Azure OpenAI resource. For more information on deployments, see [Create a resource and deploy a model with Azure OpenAI](/azure/ai-foundry/openai/how-to/create-resource).
+    - GPT-image-1 models are newer and feature a number of improvements over DALL-E 3. They are available in limited access: apply for access with [this form](https://aka.ms/oai/gptimage1access).
+
+## Overview
+
+- Use image generation via [image generation API](https://int.ai.azure.com/doc/azure/ai-foundry/openai/dall-e-quickstart?tid=7f292395-a08f-4cc0-b3d0-a400b023b0d2) or [responses API](/azure/ai-foundry/openai/how-to/responses?tabs=python-key)
+- Experiment with image generation in the [image playground](https://int.ai.azure.com/doc/azure/ai-foundry/openai/dall-e-quickstart?tid=7f292395-a08f-4cc0-b3d0-a400b023b0d2)
+- Explore [content filtering](https://int.ai.azure.com/doc/azure/ai-foundry/openai/concepts/content-filter?tid=7f292395-a08f-4cc0-b3d0-a400b023b0d2) and apply to opt out [here]([url](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUMlBQNkZMR0lFRldORTdVQzQ0TEI5Q1ExOSQlQCN0PWcu): 
+- Learn about [image generation tokens ](https://int.ai.azure.com/doc/azure/ai-foundry/openai/overview?tid=7f292395-a08f-4cc0-b3d0-a400b023b0d2)
+
+| Aspect | GPT-Image-1 | DALL·E 3 |
+|--------|-------------|----------|
+| **Input / Output Modalities & Format** | Accepts **text + image** inputs; outputs images only in **base64** (no URL option). | Accepts **text (primary)** input; limited image editing inputs (with mask). Outputs as **URL or base64**. |
+| **Image Sizes / Resolutions** | 1024×1024, 1024×1536, 1536×1024 | 1024×1024, 1024×1792, 1792×1024 |
+| **Quality Options** | `low`, `medium`, `high` (default = high) | `standard`, `hd`; style options: `natural`, `vivid` |
+| **Number of Images per Request** | 1–10 images per request (`n` parameter) | Only **1 image** per request (`n` must be 1) |
+| **Editing (inpainting / variations)** | Yes — supports inpainting and variations with mask + prompt | Yes — supports inpainting and variations |
+| **Strengths** | Better **prompt fidelity**, realism, multimodal context use, strong in **editing instruction-following** | Strong at **prompt adherence**, natural text rendering, stylistic variety, coherent image generation |
 
 
 ## Call the image generation API
@@ -321,6 +337,9 @@ The Image Edit API enables you to modify existing images based on text prompts y
 > [!IMPORTANT]
 > The input image must be less than 50 MB in size and must be a PNG or JPG file.
 
+> [!IMPORTANT]
+> `gpt-image-1-mini` does not currently support image edits.
+
 Send a POST request to:
 
 ```
@@ -381,7 +400,10 @@ The *image* value indicates the image file you want to edit.
 
 The *input_fidelity* parameter controls how much effort the model puts into matching the style and features, especially facial features, of input images. 
 
-This parameter lets you make subtle edits to an image without changing unrelated areas. When you use high input fidelity, faces are preserved more accurately than in standard mode. 
+This parameter lets you make subtle edits to an image without changing unrelated areas. When you use high input fidelity, faces are preserved more accurately than in standard mode.
+
+> [!IMPORTANT]
+> Input fidelity is not supported by the `gpt-image-1-mini` model.
 
 
 #### Mask

articles/ai-foundry/openai/how-to/prompt-caching.md

@@ -72,9 +72,9 @@ Prompt caching is supported for:
 
 |**Caching supported**|**Description**|**Supported models**|
 |--------|--------|--------|
-| **Messages** | The complete messages array: system, developer, user, and assistant content | `gpt-4o`<br/>`gpt-4o-mini`<br/>`gpt-4o-realtime-preview` (version 2024-12-17)<br/>`gpt-4o-mini-realtime-preview` (version 2024-12-17)<br>`gpt-realtime` (version 2025-08-28)<br> `o1` (version 2024-12-17) <br> `o3-mini` (version 2025-01-31) |
+| **Messages** | The complete messages array: system, developer, user, and assistant content | `gpt-4o`<br/>`gpt-4o-mini`<br/>`gpt-4o-realtime-preview` (version 2024-12-17)<br/>`gpt-4o-mini-realtime-preview` (version 2024-12-17)<br>`gpt-realtime` (version 2025-08-28)<br> `gpt-realtime-mini` (version 2025-10-06)<br>`o1` (version 2024-12-17) <br> `o3-mini` (version 2025-01-31) |
 | **Images** | Images included in user messages, both as links or as base64-encoded data. The detail parameter must be set the same across requests. | `gpt-4o`<br/>`gpt-4o-mini` <br> `o1` (version 2024-12-17)  |
-| **Tool use** | Both the messages array and tool definitions. | `gpt-4o`<br/>`gpt-4o-mini`<br/>`gpt-4o-realtime-preview` (version 2024-12-17)<br/>`gpt-4o-mini-realtime-preview` (version 2024-12-17)<br>`gpt-realtime` (version 2025-08-28)<br> `o1` (version 2024-12-17) <br> `o3-mini` (version 2025-01-31) |
+| **Tool use** | Both the messages array and tool definitions. | `gpt-4o`<br/>`gpt-4o-mini`<br/>`gpt-4o-realtime-preview` (version 2024-12-17)<br/>`gpt-4o-mini-realtime-preview` (version 2024-12-17)<br>`gpt-realtime` (version 2025-08-28)<br>`gpt-realtime-mini` (version 2025-10-06)<br> `o1` (version 2024-12-17) <br> `o3-mini` (version 2025-01-31) |
 | **Structured outputs** | Structured output schema is appended as a prefix to the system message. | `gpt-4o`<br/>`gpt-4o-mini` <br> `o1` (version 2024-12-17) <br> `o3-mini` (version 2025-01-31) |
 
 To improve the likelihood of cache hits occurring, you should structure your requests such that repetitive content occurs at the beginning of the messages array.

articles/ai-foundry/openai/how-to/realtime-audio-webrtc.md

@@ -34,6 +34,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
 - `gpt-4o-mini-realtime-preview` (2024-12-17)
 - `gpt-4o-realtime-preview` (2024-12-17)
 - `gpt-realtime` (version 2025-08-28)
+- `gpt-realtime-mini` (version 2025-10-06)
 
 You should use API version `2025-04-01-preview` in the URL for the Realtime API. The API version is included in the sessions URL.
 
@@ -45,7 +46,7 @@ Before you can use GPT real-time audio, you need:
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
 - An Azure OpenAI resource created in a [supported region](#supported-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](create-resource.md).
-- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, or `gpt-realtime` model in a supported region as described in the [supported models](#supported-models) section in this article. You can deploy the model from the [Azure AI Foundry model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
+- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, `gpt-realtime`, or `gpt-realtime-mini` model in a supported region as described in the [supported models](#supported-models) section in this article. You can deploy the model from the [Azure AI Foundry model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
 
 ## Connection and authentication
 

articles/ai-foundry/openai/how-to/realtime-audio-websockets.md

@@ -31,6 +31,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
 - `gpt-4o-mini-realtime-preview` (2024-12-17)
 - `gpt-4o-realtime-preview` (2024-12-17)
 - `gpt-realtime` (version 2025-08-28)
+- `gpt-realtime-mini` (version 2025-10-06)
 
 You should use API version `2025-04-01-preview` in the URL for the Realtime API. 
 
@@ -42,7 +43,7 @@ Before you can use GPT real-time audio, you need:
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
 - An Azure OpenAI resource created in a [supported region](#supported-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](create-resource.md).
-- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, or `gpt-realtime` model in a supported region as described in the [supported models](#supported-models) section. You can deploy the model from the [Azure AI Foundry portal model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
+- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, `gpt-realtime`, or `gpt-realtime-mini` model in a supported region as described in the [supported models](#supported-models) section. You can deploy the model from the [Azure AI Foundry portal model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
 
 ## Connection and authentication
 

articles/ai-foundry/openai/how-to/realtime-audio.md

@@ -29,6 +29,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
 - `gpt-4o-mini-realtime-preview` (2024-12-17)
 - `gpt-4o-realtime-preview` (2024-12-17)
 - `gpt-realtime` (version 2025-08-28)
+- `gpt-realtime-mini` (version 2025-10-06)
 
 You should use API version `2025-04-01-preview` in the URL for the Realtime API. 
 
@@ -40,10 +41,10 @@ Before you can use GPT real-time audio, you need:
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
 - An Azure OpenAI resource created in a [supported region](#supported-models). For more information, see [Create a resource and deploy a model with Azure OpenAI](create-resource.md).
-- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, or `gpt-realtime` model in a supported region as described in the [supported models](#supported-models) section. You can deploy the model from the [Azure AI Foundry portal model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
+- You need a deployment of the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, `gpt-realtime`, or `gpt-realtime-mini` model in a supported region as described in the [supported models](#supported-models) section. You can deploy the model from the [Azure AI Foundry portal model catalog](../../../ai-foundry/how-to/model-catalog-overview.md) or from your project in Azure AI Foundry portal. 
 
 Here are some of the ways you can get started with the GPT Realtime API for speech and audio:
-- For steps to deploy and use the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, or `gpt-realtime` model, see [the real-time audio quickstart](../realtime-audio-quickstart.md).
+- For steps to deploy and use the `gpt-4o-realtime-preview`, `gpt-4o-mini-realtime-preview`, `gpt-realtime`, or `gpt-realtime-mini` model, see [the real-time audio quickstart](../realtime-audio-quickstart.md).
 - Try the [WebRTC via HTML and JavaScript example](./realtime-audio-webrtc.md#webrtc-example-via-html-and-javascript) to get started with the Realtime API via WebRTC.
 - [The Azure-Samples/aisearch-openai-rag-audio repo](https://github.com/Azure-Samples/aisearch-openai-rag-audio) contains an example of how to implement RAG support in applications that use voice as their user interface, powered by the GPT realtime API for audio.
 
@@ -281,7 +282,7 @@ A user might want to interrupt the assistant's response or ask the assistant to
 
 ## Image input
 
-The `gpt-realtime` model supports image input as part of the conversation. The model can ground responses in what the user is currently seeing. You can send images to the model as part of a conversation item. The model can then generate responses that reference the images.
+The `gpt-realtime` and `gpt-realtime-mini` models support image input as part of the conversation. The model can ground responses in what the user is currently seeing. You can send images to the model as part of a conversation item. The model can then generate responses that reference the images.
 
 The following example json body adds an image to the conversation:
 

articles/ai-foundry/openai/how-to/responses.md

@@ -58,6 +58,7 @@ The responses API is currently available in the following regions:
 - `gpt-4.1-nano` (Version: `2025-04-14`)
 - `gpt-4.1-mini` (Version: `2025-04-14`)
 - `gpt-image-1` (Version: `2025-04-15`)
+- `gpt-image-1-mini` (Version: `2025-10-06`)
 - `o1` (Version: `2024-12-17`)
 - `o3-mini` (Version: `2025-01-31`)
 - `o3` (Version: `2025-04-16`)
@@ -1268,7 +1269,7 @@ Compared to the standalone Image API, the Responses API offers several advantage
 * **Flexible inputs**: Accept image File IDs as inputs, in addition to raw image bytes.
 
 > [!NOTE]
-> The image generation tool in the Responses API is only supported by the `gpt-image-1` model. You can however call this model from this list of supported models - `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `o3`, and `gpt-5` series models.<br><br>The Responses API image generation tool does not currently support streaming mode. To use streaming mode and generate partial images, call the [image generation API](./dall-e.md) directly outside of the Responses API.
+> The image generation tool in the Responses API is only supported by the `gpt-image-1` series models. You can however call this model from this list of supported models - `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `o3`, and `gpt-5` series models.<br><br>The Responses API image generation tool does not currently support streaming mode. To use streaming mode and generate partial images, call the [image generation API](./dall-e.md) directly outside of the Responses API.
 
 Use the Responses API if you want to build conversational image experiences with GPT Image.
 

articles/ai-foundry/openai/includes/dall-e-rest.md

@@ -19,7 +19,7 @@ Use this guide to get started calling the Azure OpenAI in Azure AI Foundry Model
 - <a href="https://www.python.org/" target="_blank">Python 3.8 or later version</a>.
 - The following Python libraries installed: `os`, `requests`, `json`.
 - An Azure OpenAI resource created in a supported region. See [Region availability](/azure/ai-foundry/openai/concepts/models#model-summary-table-and-region-availability).
-- Then, you need to deploy a `gpt-image-1` or `dalle3` model with your Azure resource. For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
+- Then, you need to deploy a `gpt-image-1`-series or `dalle3` model with your Azure resource. For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
 
 ## Setup