Skip to content

Commit 7708062

Browse files
Merge pull request #6618 from MicrosoftDocs/main
Auto Publish – main to live - 2025-08-16 05:03 UTC
2 parents 80a6ada + 56d0587 commit 7708062

File tree

3 files changed

+17
-18
lines changed

3 files changed

+17
-18
lines changed

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

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -55,9 +55,9 @@ Azure OpenAI is powered by a diverse set of models with different capabilities a
5555

5656
| Model ID | Description | Context Window | Max Output Tokens | Training Data (up to) |
5757
| --- | :--- |:--- |:---|:---: |
58-
| `gpt-5` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 272,000 | 128,000 | October 24, 2024 |
59-
| `gpt-5-mini` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 272,000 | 128,000 | June 24, 2024 |
60-
| `gpt-5-nano` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 272,000 | 128,000 | May 31, 2024 |
58+
| `gpt-5` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 400,000<br><br>Input: 272,000<br>Output: 128,000 | 128,000 | October 24, 2024 |
59+
| `gpt-5-mini` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 400,000<br><br>Input: 272,000<br>Output: 128,000 | 128,000 | June 24, 2024 |
60+
| `gpt-5-nano` (2025-08-07) | - [Reasoning](../how-to/reasoning.md) <br> - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - Structured outputs.<br> - Text and image processing. <br> - Functions, tools, and parallel tool calling. <br> [Full summary of capabilities](../how-to/reasoning.md). | 400,000<br><br>Input: 272,000<br>Output: 128,000 | 128,000 | May 31, 2024 |
6161
| `gpt-5-chat` (2025-08-07)<br>**Preview** | - Chat Completions API. <br> - [Responses API](../how-to/responses.md). <br> - **Input**: Text/Image <br> - **Output**: Text only | 128,000 | 16,384 | October 24, 2024 |
6262

6363
## gpt-oss

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

Lines changed: 13 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: Learn how to use Azure OpenAI's advanced GPT-5 series, o3-mini, o1,
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: include
8-
ms.date: 08/06/2025
8+
ms.date: 08/15/2025
99
author: mrbullwinkle
1010
ms.author: mbullwin
1111
---
@@ -29,8 +29,8 @@ Azure OpenAI reasoning models are designed to tackle reasoning and problem-solvi
2929
| Model | Region | Limited access |
3030
|---|---|---|
3131
| `gpt-5` | East US2 & Sweden Central (Global Standard & Data Zones) | Request access: [gpt-5 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 & Data Zones) | No access request needed to use the core capabilities of this model |
33-
| `gpt-5-nano` | East US2 & Sweden Central (Global Standard & Data Zones) | No access request needed to use the core capabilities of this model |
32+
| `gpt-5-mini` | East US2 & Sweden Central (Global Standard & Data Zones) | No access request needed. |
33+
| `gpt-5-nano` | East US2 & Sweden Central (Global Standard & Data Zones) | No access request needed. |
3434
| `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. |
3535
| `codex-mini` | East US2 & Sweden Central (Global Standard) | No access request needed. |
3636
| `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) |
@@ -49,7 +49,7 @@ Azure OpenAI reasoning models are designed to tackle reasoning and problem-solvi
4949
| **API Version** | [v1 preview](../api-version-lifecycle.md#api-evolution) | [v1 preview](../api-version-lifecycle.md#api-evolution) | [v1 preview](../api-version-lifecycle.md#api-evolution) |
5050
| **[Developer Messages](#developer-messages)** ||||
5151
| **[Structured Outputs](./structured-outputs.md)** ||||
52-
| **[Context Window](../concepts/models.md#o-series-models)** | Input: 272,000 <br> Output: 128,000 | Input: 272,000 <br> Output: 128,000 | Input: 272,000 <br> Output: 128,000 |
52+
| **[Context Window](../concepts/models.md#o-series-models)** | 400,000 <br><br>Input: 272,000 <br> Output: 128,000 | 400,000 <br><br> Input: 272,000 <br> Output: 128,000 | 400,000 <br><br> Input: 272,000 <br> Output: 128,000 |
5353
| **[Reasoning effort](#reasoning-effort)** ||||
5454
| **[Image input](./gpt-with-vision.md)** ||||
5555
| Chat Completions API ||||
@@ -58,13 +58,13 @@ Azure OpenAI reasoning models are designed to tackle reasoning and problem-solvi
5858
| Parallel Tool Calls<sup>1</sup> ||||
5959
| `max_completion_tokens` <sup>2</sup> ||||
6060
| System Messages <sup>3</sup> ||||
61-
| [Reasoning summary](#reasoning-summary) <sup>4</sup> || - | - |
61+
| [Reasoning summary](#reasoning-summary) || | |
6262
| Streaming ||||
6363

6464
<sup>1</sup> Parallel tool calls are not supported when `reasoning_effort` is set to `minimal`<br><br>
6565
<sup>2</sup> Reasoning models will only work with the `max_completion_tokens` parameter when using the Chat Completions API. Use `max_output_tokens` with the Responses API. <br><br>
6666
<sup>3</sup> The latest reasoning models support system messages to make migration easier. You should not use both a developer message and a system message in the same API request.<br><br>
67-
<sup>4</sup> Access to the chain-of-thought reasoning summary is limited access only for `o3` & `o4-mini`.
67+
6868

6969
### NEW GPT-5 reasoning features
7070

@@ -95,13 +95,12 @@ For more information, we also recommend reading OpenAI's [GPT-5 prompting cookbo
9595
| Parallel Tool Calls | - | - | - | - | - | - | - |
9696
| `max_completion_tokens` <sup>1</sup> ||||||||
9797
| System Messages <sup>2</sup> ||||||| - |
98-
| [Reasoning summary](#reasoning-summary) <sup>3</sup> || - ||| - | - | - |
99-
| Streaming <sup>4</sup> || - |||| - | - |
98+
| [Reasoning summary](#reasoning-summary) || - ||| - | - | - |
99+
| Streaming <sup>3</sup> || - |||| - | - |
100100

101101
<sup>1</sup> Reasoning models will only work with the `max_completion_tokens` parameter when using the Chat Completions API. Use `max_output_tokens` with the Responses API.<br><br>
102102
<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.
103-
<sup>3</sup> Access to the chain-of-thought reasoning summary is limited access only for `o3` & `o4-mini`.
104-
<sup>4</sup> Streaming for `o3` is limited access only.
103+
<sup>3</sup> Streaming for `o3` is limited access only.
105104

106105
---
107106

@@ -432,10 +431,10 @@ Console.WriteLine($"{completion.Role}: {completion.Content[0].Text}");
432431

433432
## Reasoning summary
434433

435-
When using the latest reasoning models with the [Responses API](./responses.md) you can use the reasoning summary parameter to receive summaries of the model's chain of thought reasoning. This parameter can be set to `auto`, `concise`, or `detailed`. Access to this feature requires you to [Request Access](https://aka.ms/oai/o3access).
434+
When using the latest reasoning models with the [Responses API](./responses.md) you can use the reasoning summary parameter to receive summaries of the model's chain of thought reasoning.
436435

437436
> [!NOTE]
438-
> Even when enabled, reasoning summaries are not generated for every step/request. This is expected behavior.
437+
> Even when enabled, reasoning summaries are not guaranteed to be generated for every step/request. This is expected behavior.
439438
440439
# [Python](#tab/py)
441440

@@ -464,8 +463,8 @@ response = client.responses.create(
464463
model="gpt-5", # replace with model deployment name
465464
reasoning={
466465
"effort": "medium",
467-
"summary": "auto" # auto, concise, or detailed
468-
}
466+
"summary": "auto" # auto, concise, or detailed, gpt-5 series do not support concise
467+
},
469468
text={
470469
"verbosity": "low" # New with GPT-5 models
471470
}

articles/search/search-security-overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -92,7 +92,7 @@ Internal requests are secured and managed by Microsoft. You can't configure or c
9292
Internal traffic consists of:
9393

9494
+ Service-to-service calls for tasks like authentication and authorization through Microsoft Entra ID, resource logging sent to Azure Monitor, and [private endpoint connections](service-create-private-endpoint.md) that utilize Azure Private Link.
95-
+ Requests made to Azure AI services APIs for [built-in skills](cognitive-search-predefined-skills.md)
95+
+ Requests for [built-in skills processing](cognitive-search-predefined-skills.md), with same-region requests directed to an internally hosted Azure AI multi-service resource used exclusively for built-in skills processing by Azure AI Search.
9696
+ Requests made to the various models that support [semantic ranking](semantic-search-overview.md#availability-and-pricing).
9797

9898
<a name="service-access-and-authentication"></a>

0 commit comments

Comments
 (0)