Skip to content

Commit 5ea42d0

Browse files
mrbullwinklemrbullwinkle
committed
update
1 parent a48b13a commit 5ea42d0

File tree

1 file changed

+31
-22
lines changed

1 file changed

+31
-22
lines changed

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

Lines changed: 31 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -1,21 +1,21 @@
11
---
2-
title: Azure OpenAI reasoning models - o3-mini, o1, o1-mini
2+
title: Azure OpenAI reasoning models - GPT-5 series, o3-mini, o1, o1-mini
33
titleSuffix: Azure OpenAI
4-
description: Learn how to use Azure OpenAI's advanced o3-mini, o1, & o1-mini reasoning models
4+
description: Learn how to use Azure OpenAI's advanced GPT-5 series, o3-mini, o1, & o1-mini reasoning models
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: include
8-
ms.date: 07/08/2025
8+
ms.date: 08/06/2025
99
author: mrbullwinkle
1010
ms.author: mbullwin
1111
---
1212

1313

1414
# Azure OpenAI reasoning models
1515

16-
Azure OpenAI `o-series` models are designed to tackle reasoning and problem-solving tasks with increased focus and capability. These models spend more time processing and understanding the user's request, making them exceptionally strong in areas like science, coding, and math compared to previous iterations.
16+
Azure OpenAI reasoning models are designed to tackle reasoning and problem-solving tasks with increased focus and capability. These models spend more time processing and understanding the user's request, making them exceptionally strong in areas like science, coding, and math compared to previous iterations.
1717

18-
**Key capabilities of the o-series models:**
18+
**Key capabilities of reasoning models:**
1919

2020
- Complex Code Generation: Capable of generating algorithms and handling advanced coding tasks to support developers.
2121
- Advanced Problem Solving: Ideal for comprehensive brainstorming sessions and addressing multifaceted challenges.
@@ -28,7 +28,10 @@ Azure OpenAI `o-series` models are designed to tackle reasoning and problem-solv
2828

2929
| Model | Region | Limited access |
3030
|---|---|---|
31-
| `o3-pro` | East US2 & Sweden Central (Global Standard) | Request access: [o3 limited access model application](https://aka.ms/oai/o3access). If you already have `o3 access` no request is required for `o3-pro`. |
31+
| `gpt-5` | East US2 & Sweden Central (Global Standard) | Request access: [gpt-5 series limited access model application](https://aka.ms/oai/gpt5access). If you already have `o3 access` no request is required |
32+
| `gpt-5-mini` | East US2 & Sweden Central (Global Standard) | Request access: [gpt-5 series limited access model application](https://aka.ms/oai/gpt5access). If you already have `o3 access` no request is required |
33+
| `gpt-5-nano` | East US2 & Sweden Central (Global Standard) | Request access: [gpt-5 series limited access model application](https://aka.ms/oai/gpt5access). If you already have `o3 access` no request is required |
34+
| `o3-pro` | East US2 & Sweden Central (Global Standard) | Request access: [o3 limited access model application](https://aka.ms/oai/o3access). If you already have `o3 access` no request is required. |
3235
| `codex-mini` | East US2 & Sweden Central (Global Standard) | No access request needed. |
3336
| `o4-mini` | [Model availability](../concepts/models.md#global-standard-model-availability) | No access request needed to use the core capabilities of this model.<br><br> Request access: [o4-mini reasoning summary feature](https://aka.ms/oai/o3access) |
3437
| `o3` | [Model availability](../concepts/models.md#global-standard-model-availability) | Request access: [o3 limited access model application](https://aka.ms/oai/o3access) |
@@ -39,28 +42,34 @@ Azure OpenAI `o-series` models are designed to tackle reasoning and problem-solv
3942

4043
## API & feature support
4144

42-
| **Feature** | **codex-mini**, **2025-05-16** | **o3-pro**, **2025-06-10** | **o4-mini**, **2025-04-16** | **o3**, **2025-04-16** | **o3-mini**, **2025-01-31** |**o1**, **2024-12-17** | **o1-preview**, **2024-09-12** | **o1-mini**, **2024-09-12** |
43-
|:-------------------|:--------------------------:|:------:|:--------|:-----:|:-------:|:--------------------------:|:-------------------------------:|:---:|
44-
| **API Version** | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) |
45-
| **[Developer Messages](#developer-messages)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - | - |
46-
| **[Structured Outputs](./structured-outputs.md)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - | - |
47-
| **[Context Window](../concepts/models.md#o-series-models)** | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 128,000 <br> Output: 32,768 | Input: 128,000 <br> Output: 65,536 |
48-
| **[Reasoning effort](#reasoning-effort)** | ✅| ✅| ✅| ✅ |✅ | ✅ | - | - |
49-
| **[Image input](./gpt-with-vision.md)** | ✅ | ✅ | ✅ | ✅ | - | ✅ | - | - |
50-
| Chat Completions API | - | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
51-
| Responses API | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - | - |
52-
| Functions/Tools | ✅ | ✅ |✅ | ✅ | ✅ | ✅ | - | - |
53-
| Parallel Tool Calls | - | - | - | - | - | - | - | - |
54-
| `max_completion_tokens` <sup>1</sup> | ✅ | ✅ | ✅ | ✅ |✅ |✅ |✅ | ✅ |
55-
| System Messages <sup>2</sup> | ✅ | ✅| ✅ | ✅ | ✅ | ✅ | - | - |
56-
| [Reasoning summary](#reasoning-summary) <sup>3</sup> | ✅ | - | ✅ | ✅ | - | - | - | - |
57-
| Streaming <sup>4</sup> | ✅ | - | ✅ | ✅| ✅ | - | - | - |
45+
# [GPT-5 Reasoning Models](#tab/gpt-5)
46+
47+
# [O-Series Reasoning Models](#tab/o-series)
48+
49+
| **Feature** | **codex-mini**, **2025-05-16** | **o3-pro**, **2025-06-10** | **o4-mini**, **2025-04-16** | **o3**, **2025-04-16** | **o3-mini**, **2025-01-31** |**o1**, **2024-12-17** | **o1-mini**, **2024-09-12** |
50+
|:-------------------|:--------------------------:|:------:|:--------|:-----:|:-------:|:--------------------------:|:---:|
51+
| **API Version** | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) | | `2025-04-01-preview` & [v1 preview](../api-version-lifecycle.md#api-evolution) |
52+
| **[Developer Messages](#developer-messages)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - |
53+
| **[Structured Outputs](./structured-outputs.md)** | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - |
54+
| **[Context Window](../concepts/models.md#o-series-models)** | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 200,000 <br> Output: 100,000 | Input: 128,000 <br> Output: 65,536 |
55+
| **[Reasoning effort](#reasoning-effort)** | ✅| ✅| ✅| ✅ |✅ | ✅ | - |
56+
| **[Image input](./gpt-with-vision.md)** | ✅ | ✅ | ✅ | ✅ | - | ✅ | - |
57+
| Chat Completions API | - | - | ✅ | ✅ | ✅ | ✅ | ✅ |
58+
| Responses API | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - |
59+
| Functions/Tools | ✅ | ✅ |✅ | ✅ | ✅ | ✅ | - |
60+
| Parallel Tool Calls | - | - | - | - | - | - | - |
61+
| `max_completion_tokens` <sup>1</sup> | ✅ | ✅ | ✅ | ✅ |✅ |✅ | ✅ |
62+
| System Messages <sup>2</sup> | ✅ | ✅| ✅ | ✅ | ✅ | ✅ | - |
63+
| [Reasoning summary](#reasoning-summary) <sup>3</sup> | ✅ | - | ✅ | ✅ | - | - | - |
64+
| Streaming <sup>4</sup> | ✅ | - | ✅ | ✅| ✅ | - | - |
5865

5966
<sup>1</sup> Reasoning models will only work with the `max_completion_tokens` parameter. <br><br>
6067
<sup>2</sup> The latest o<sup>&#42;</sup> series model support system messages to make migration easier. When you use a system message with `o4-mini`, `o3`, `o3-mini`, and `o1` it will be treated as a developer message. You should not use both a developer message and a system message in the same API request.
6168
<sup>3</sup> Access to the chain-of-thought reasoning summary is limited access only for `o3` & `o4-mini`.
6269
<sup>4</sup> Streaming for `o3` is limited access only.
6370

71+
---
72+
6473
> [!NOTE]
6574
> - To avoid timeouts [background mode](./responses.md#background-tasks) is recommended for `o3-pro`.
6675
> - `o3-pro` does not currently support image generation.

0 commit comments

Comments
 (0)