Updated GitHub Models rate limit table (#55327)

Co-authored-by: Siara <108543037+SiaraMist@users.noreply.github.com>

Author: JarylW

content/github-models/prototyping-with-ai-models.md

@@ -255,26 +255,26 @@ Low, high, and embedding models have different rate limits. To see which type of
     <td>1</td>
   </tr>
   <tr>
-    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>Azure OpenAI o1-mini</b></th>
+    <th rowspan="4" scope="rowgroup"><b>Azure OpenAI o1 and o3</b></th>
     <th style="padding-left: 0"><b>Requests per minute</b></th>
     <td>Not applicable</td>
+    <td>1</td>
+    <td>2</td>
     <td>2</td>
-    <td>3</td>
-    <td>3</td>
   </tr>
   <tr>
     <th><b>Requests per day</b></th>
     <td>Not applicable</td>
+    <td>8</td>
+    <td>10</td>
     <td>12</td>
-    <td>15</td>
-    <td>20</td>
   </tr>
   <tr>
     <th><b>Tokens per request</b></th>
     <td>Not applicable</td>
     <td>4000 in, 4000 out</td>
     <td>4000 in, 4000 out</td>
-    <td>4000 in, 4000 out</td>
+    <td>4000 in, 8000 out</td>
   </tr>
   <tr>
     <th><b>Concurrent requests</b></th>
@@ -284,7 +284,7 @@ Low, high, and embedding models have different rate limits. To see which type of
     <td>1</td>
   </tr>
   <tr>
-    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>Azure OpenAI o3-mini</b></th>
+    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>Azure OpenAI o1-mini, o3-mini, and o4-mini</b></th>
     <th style="padding-left: 0"><b>Requests per minute</b></th>
     <td>Not applicable</td>
     <td>2</td>
@@ -313,7 +313,7 @@ Low, high, and embedding models have different rate limits. To see which type of
     <td>1</td>
   </tr>
   <tr>
-    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>DeepSeek-R1</b></th>
+    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>DeepSeek-R1 and MAI-DS-R1</b></th>
     <th style="padding-left: 0"><b>Requests per minute</b></th>
     <td>1</td>
     <td>1</td>