You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|**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) |
77
-
|**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) |
77
+
|**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) |
78
78
|**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) |
79
79
80
80
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.
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/how-to/realtime-audio-webrtc.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -34,6 +34,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
34
34
-`gpt-4o-mini-realtime-preview` (2024-12-17)
35
35
-`gpt-4o-realtime-preview` (2024-12-17)
36
36
-`gpt-realtime` (version 2025-08-28)
37
+
-`gpt-realtime-mini` (version 2025-10-06)
37
38
38
39
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.
39
40
@@ -45,7 +46,7 @@ Before you can use GPT real-time audio, you need:
45
46
46
47
- An Azure subscription - <ahref="https://azure.microsoft.com/free/cognitive-services"target="_blank">Create one for free</a>.
47
48
- 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).
48
-
- 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.
49
+
- 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.
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/how-to/realtime-audio-websockets.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -31,6 +31,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
31
31
-`gpt-4o-mini-realtime-preview` (2024-12-17)
32
32
-`gpt-4o-realtime-preview` (2024-12-17)
33
33
-`gpt-realtime` (version 2025-08-28)
34
+
-`gpt-realtime-mini` (version 2025-10-06)
34
35
35
36
You should use API version `2025-04-01-preview` in the URL for the Realtime API.
36
37
@@ -42,7 +43,7 @@ Before you can use GPT real-time audio, you need:
42
43
43
44
- An Azure subscription - <ahref="https://azure.microsoft.com/free/cognitive-services"target="_blank">Create one for free</a>.
44
45
- 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).
45
-
- 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.
46
+
- 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.
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/how-to/realtime-audio.md
+4-3Lines changed: 4 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,6 +29,7 @@ The GPT real-time models are available for global deployments in [East US 2 and
29
29
-`gpt-4o-mini-realtime-preview` (2024-12-17)
30
30
-`gpt-4o-realtime-preview` (2024-12-17)
31
31
-`gpt-realtime` (version 2025-08-28)
32
+
-`gpt-realtime-mini` (version 2025-10-06)
32
33
33
34
You should use API version `2025-04-01-preview` in the URL for the Realtime API.
34
35
@@ -40,10 +41,10 @@ Before you can use GPT real-time audio, you need:
40
41
41
42
- An Azure subscription - <ahref="https://azure.microsoft.com/free/cognitive-services"target="_blank">Create one for free</a>.
42
43
- 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).
43
-
- 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.
44
+
- 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.
44
45
45
46
Here are some of the ways you can get started with the GPT Realtime API for speech and audio:
46
-
- 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).
47
+
- 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).
47
48
- 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.
48
49
-[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.
49
50
@@ -281,7 +282,7 @@ A user might want to interrupt the assistant's response or ask the assistant to
281
282
282
283
## Image input
283
284
284
-
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.
285
+
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.
285
286
286
287
The following example json body adds an image to the conversation:
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/includes/realtime-python.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -13,7 +13,7 @@ ms.date: 3/20/2025
13
13
- An Azure subscription. <ahref="https://azure.microsoft.com/free/ai-services"target="_blank">Create one for free</a>.
14
14
- <ahref="https://www.python.org/"target="_blank">Python 3.8 or later version</a>. We recommend using Python 3.10 or later, but having at least Python 3.8 is required. If you don't have a suitable version of Python installed, you can follow the instructions in the [VS Code Python Tutorial](https://code.visualstudio.com/docs/python/python-tutorial#_install-a-python-interpreter) for the easiest way of installing Python on your operating system.
15
15
- An Azure OpenAI resource created in one of the supported regions. For more information about region availability, see the [models and versions documentation](../concepts/models.md#global-standard-model-availability).
16
-
- Then, you need to deploy a `gpt-realtime` model with your Azure OpenAI resource. For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
16
+
- Then, you need to deploy a `gpt-realtime`or `gpt-realtime-mini`model with your Azure OpenAI resource. For more information, see [Create a resource and deploy a model with Azure OpenAI](../how-to/create-resource.md).
0 commit comments