jprdonnelly/docs
1
0
Fork 0
mirror of synced 2025-12-19 18:10:59 -05:00
Code Issues Projects Releases Wiki Activity

Update rate limits for o1 models (#52377)

Browse Source 
Co-authored-by: Will Perry <willpe@github.com>
Co-authored-by: skedwards88 <skedwards88@github.com>
This commit is contained in:
Matthew Isabel
2024-09-20 18:23:05 -04:00
committed by GitHub
parent 6f9180ad41
commit e8164ae521
1 changed files with 51 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
content/github-models/prototyping-with-ai-models.md
View File

@@ -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.