From e8164ae52136cf3c5810ff31d37e49a01cb4006b Mon Sep 17 00:00:00 2001
From: Matthew Isabel <matthewisabel@github.com>
Date: Fri, 20 Sep 2024 18:23:05 -0400
Subject: [PATCH] Update rate limits for o1 models (#52377)

Co-authored-by: Will Perry <willpe@github.com>
Co-authored-by: skedwards88 <skedwards88@github.com>
---
 .../prototyping-with-ai-models.md             | 52 ++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/content/github-models/prototyping-with-ai-models.md b/content/github-models/prototyping-with-ai-models.md
index 4a341cf4194f..3ba7b9f51069 100644
--- a/content/github-models/prototyping-with-ai-models.md
+++ b/content/github-models/prototyping-with-ai-models.md
@@ -126,7 +126,7 @@ Low, high, and embedding models have different rate limits. To see which type of
     <td>4</td>
   </tr>
   <tr>
-    <th rowspan="4" scope="rowgroup" style="box-shadow: none"><b>Embedding</b></th>
+    <th rowspan="4" scope="rowgroup"><b>Embedding</b></th>
     <th style="padding-left: 0"><b>Requests per minute</b></th>
     <td>15</td>
     <td>15</td>
@@ -150,6 +150,56 @@ Low, high, and embedding models have different rate limits. To see which type of
     <td>5</td>
     <td>8</td>
   </tr>
+  <tr>
+    <th rowspan="4" scope="rowgroup"><b>Azure OpenAI o1-preview</b></th>
+    <th style="padding-left: 0"><b>Requests per minute</b></th>
+    <td>1</td>
+    <td>2</td>
+    <td>2</td>
+  </tr>
+  <tr>
+    <th><b>Requests per day</b></th>
+    <td>8</td>
+    <td>10</td>
+    <td>12</td>
+  </tr>
+  <tr>
+    <th><b>Tokens per request</b></th>
+    <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>
+    <td>1</td>
+    <td>1</td>
+    <td>1</td>
+  </tr>
+  <tr>
+    <th rowspan="4" scope="rowgroup"  style="box-shadow: none"><b>Azure OpenAI o1-mini</b></th>
+    <th style="padding-left: 0"><b>Requests per minute</b></th>
+    <td>2</td>
+    <td>3</td>
+    <td>3</td>
+  </tr>
+  <tr>
+    <th><b>Requests per day</b></th>
+    <td>12</td>
+    <td>15</td>
+    <td>20</td>
+  </tr>
+  <tr>
+    <th><b>Tokens per request</b></th>
+    <td>4000 in, 4000 out</td>
+    <td>4000 in, 4000 out</td>
+    <td>4000 in, 4000 out</td>
+  </tr>
+  <tr>
+    <th><b>Concurrent requests</b></th>
+    <td>1</td>
+    <td>1</td>
+    <td>1</td>
+  </tr>
 </table>
 
 These limits are subject to change without notice.