Skip to content

Commit d10d23e

Browse files
Merge pull request #3565 from mrbullwinkle/mrb_03_17_2025_models
[Azure OpenAI] [Release branch] Update models page
2 parents ff58bb8 + c32f03d commit d10d23e

File tree

1 file changed

+30
-1
lines changed
  • articles/ai-services/openai/concepts

1 file changed

+30
-1
lines changed

articles/ai-services/openai/concepts/models.md

Lines changed: 30 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
44
description: Learn about the different model capabilities that are available with Azure OpenAI.
55
ms.service: azure-ai-openai
66
ms.topic: conceptual
7-
ms.date: 03/10/2025
7+
ms.date: 03/17/2025
88
ms.custom: references_regions, build-2023, build-2023-dataai, refefences_regions
99
manager: nitinme
1010
author: mrbullwinkle #ChrisHMSFT
@@ -18,6 +18,7 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
1818

1919
| Models | Description |
2020
|--|--|
21+
| [computer-use-preview](#computer-use-preview) | An experimental model trained for use with the Responses API computer use tool. |
2122
| [GPT-4.5 Preview](#gpt-45-preview) |The latest GPT model that excels at diverse text and image tasks. |
2223
| [o-series models](#o-series-models) |[Reasoning models](../how-to/reasoning.md) with advanced problem-solving and increased focus and capability. |
2324
| [GPT-4o & GPT-4o mini & GPT-4 Turbo](#gpt-4o-and-gpt-4-turbo) | The latest most capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
@@ -29,6 +30,34 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
2930
| [Whisper](#whisper-models) | A series of models in preview that can transcribe and translate speech to text. |
3031
| [Text to speech](#text-to-speech-models-preview) (Preview) | A series of models in preview that can synthesize text to speech. |
3132

33+
## computer-use-preview
34+
35+
An experimental model trained for use with the [Responses API](../how-to/responses.md) computer use tool. It can be used in conjunction with 3rd-party libraries to allow the model to control mouse & keyboard input while getting context from screenshots of the current environment.
36+
37+
> [!CAUTION]
38+
> We don't recommend using preview models in production. We will upgrade all deployments of preview models to either future preview versions or to the latest stable GA version. Models that are designated preview don't follow the standard Azure OpenAI model lifecycle.
39+
40+
### Availability
41+
42+
**For access to `computer-use-preview` registration is required, and access will be granted based on Microsoft's eligibility criteria**. Customers who have access to other limited access models will still need to request access for this model.
43+
44+
Request access: [`computer-use-preview` limited access model application](https://aka.ms/oai/cuaaccess)
45+
46+
Once access has been granted, you will need to create a deployment for the model.
47+
48+
### Region Availability
49+
50+
| Model | Region |
51+
|---|---|
52+
| `computer-use-preview` | East US 2 (Global Standard) <br> South India (Global Standard) <br> Sweden Central (Global Standard) |
53+
54+
### Capabilities
55+
56+
| Model ID | Description | Context Window | Max Output Tokens | Training Data (up to) |
57+
| --- | :--- |:--- |:---|:---: |
58+
| `computer-use-preview` (2025-03-11) | Specialized model for use with the [Responses API](../how-to/responses.md) computer use tool <br> <br>-Tools <br>-Streaming<br>-Text(input/output)<br>- Image(input) | 8,192 | 1,024 | Oct 2023 |
59+
60+
3261
## GPT-4.5 Preview
3362

3463
### Availability

0 commit comments

Comments
 (0)