Merge pull request #3803 from mrbullwinkle/patch-33

Update reasoning.md

Author: prmerger-automator[bot]

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

@@ -37,7 +37,7 @@ Azure OpenAI `o-series` models are designed to tackle reasoning and problem-solv
 
 | **Feature**     | **o3-mini**, **2025-01-31**  |**o1**, **2024-12-17**   | **o1-preview**, **2024-09-12**   | **o1-mini**, **2024-09-12**   |
 |:-------------------|:--------------------------:|:--------------------------:|:-------------------------------:|:---:|
-| **API Version**    | `2024-12-01-preview` <br> `2025-01-01-preview`   | `2024-12-01-preview` <br> `2025-01-01-preview` | `2024-09-01-preview`  <br> `2024-10-01-preview` <br> `2024-12-01-preview`    | `2024-09-01-preview`  <br> `2024-10-01-preview` <br> `2024-12-01-preview`    |
+| **API Version**    | `2024-12-01-preview` or later <br> 2025-03-01-preview (Recommended)   | `2024-12-01-preview` or later <br> 2025-03-01-preview (Recommended) | `2024-09-01-preview` or later <br> 2025-03-01-preview (Recommended)    | `2024-09-01-preview` or later <br> 2025-03-01-preview (Recommended)    |
 | **[Developer Messages](#developer-messages)** | ✅ | ✅ | - | - |
 | **[Structured Outputs](./structured-outputs.md)** | ✅ | ✅ | - | - |
 | **[Context Window](../concepts/models.md#o-series-models)** | 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 |
@@ -320,4 +320,4 @@ To improve the performance of `Formatting re-enabled` you can further augment th
 - `Formatting re-enabled - please enclose code blocks with appropriate markdown tags.`
 - `Formatting re-enabled - code output should be wrapped in markdown.`
 
-Depending on your expected output you may need to customize your initial developer message further to target your specific use case.
+Depending on your expected output you may need to customize your initial developer message further to target your specific use case.