glhf: update rate limits

src/pull_available_models.py

@@ -798,9 +798,9 @@ def main():
 
     table += """<tr>
         <td><a href="https://glhf.chat/" target="_blank">glhf.chat (Free Beta)</a></td>
-        <td>Email for API access</td>
-        <td>Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8</td>
         <td></td>
+        <td>Any model on Hugging Face runnable on vLLM and fits on a A100 node (~640GB VRAM), including Llama 3.1 405B at FP8</td>
+        <td><a href="https://glhf.chat/pages/faq#whats-the-rate-limit">480 requests/8 hours</a></td>
     </tr>"""
 
     table += "</tbody></table>"