<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0 in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/permission-denied-the-endpoint-is-temporarily-disabled-due-to-a/m-p/150800#M1695</link>
    <description>&lt;P&gt;Greetings&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/219770"&gt;@itssb&lt;/a&gt;&amp;nbsp;, I did some digging and here is what I found:&lt;/P&gt;
&lt;P class="p1"&gt;What you are seeing is a Databricks-imposed rate limit of 0, and that setting takes precedence over the endpoint- or user-level rate limits you configured in the UI. In other words, even if you set non-zero QPM or TPM values in Serving or AI Gateway, those settings will not override this restriction.&lt;/P&gt;
&lt;P class="p1"&gt;This is expected behavior for certain high-demand hosted models, including GPT-5.x and some Claude variants, when used from &lt;STRONG&gt;trial or Free&lt;/STRONG&gt; Edition workspaces. In those cases, the workspace is often placed in a TRIAL_VERIFIED trust tier, which can block or heavily restrict access to premium models regardless of the limits shown in the UI.&lt;/P&gt;
&lt;P class="p1"&gt;The key point is this: the “rate limit of 0” error is not something that can be fixed by adjusting endpoint settings. It reflects a workspace-level access restriction for that model.&lt;/P&gt;
&lt;P class="p1"&gt;The path forward is one of the following:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;
&lt;P class="p1"&gt;Upgrade the workspace to a paid / fully enabled subscription&lt;/P&gt;
&lt;/LI&gt;
&lt;LI&gt;
&lt;P class="p1"&gt;Work with Databricks Sales or Support to have the workspace converted so it is fully enabled for those premium hosted models&lt;/P&gt;
&lt;/LI&gt;
&lt;/UL&gt;
&lt;P class="p1"&gt;Once the workspace is moved to a PAYABLE_VERIFIED tier, this Databricks-set rate limit of 0 typically disappears, and the same endpoint will often begin working without any additional UI changes.&lt;/P&gt;
&lt;P class="p1"&gt;In the meantime, the practical workaround is to use open-source or otherwise non-gated models, such as Llama, which are not subject to this specific Databricks-imposed 0-rate-limit restriction.&lt;/P&gt;
&lt;P class="p1"&gt;Hope this helps, Louis.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Fri, 13 Mar 2026 12:41:22 GMT</pubDate>
    <dc:creator>Louis_Frolio</dc:creator>
    <dc:date>2026-03-13T12:41:22Z</dc:date>
    <item>
      <title>PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0</title>
      <link>https://community.databricks.com/t5/generative-ai/permission-denied-the-endpoint-is-temporarily-disabled-due-to-a/m-p/150773#M1690</link>
      <description>&lt;P&gt;I'm new to databricks and been trying to test some AI models through the AI gateway, every model I try, it gives me error:&lt;/P&gt;&lt;P&gt;"error_code":"PERMISSION_DENIED","message":"PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0."}%&lt;/P&gt;&lt;P&gt;I tried to set the rate limits too, as shown in the picture, but that didn't work either. I have entered credit card details, so not a free trial account limit.&lt;/P&gt;&lt;P&gt;How can I fix this?&lt;/P&gt;</description>
      <pubDate>Fri, 13 Mar 2026 10:08:59 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/permission-denied-the-endpoint-is-temporarily-disabled-due-to-a/m-p/150773#M1690</guid>
      <dc:creator>itssb</dc:creator>
      <dc:date>2026-03-13T10:08:59Z</dc:date>
    </item>
    <item>
      <title>Re: PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0</title>
      <link>https://community.databricks.com/t5/generative-ai/permission-denied-the-endpoint-is-temporarily-disabled-due-to-a/m-p/150800#M1695</link>
      <description>&lt;P&gt;Greetings&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/219770"&gt;@itssb&lt;/a&gt;&amp;nbsp;, I did some digging and here is what I found:&lt;/P&gt;
&lt;P class="p1"&gt;What you are seeing is a Databricks-imposed rate limit of 0, and that setting takes precedence over the endpoint- or user-level rate limits you configured in the UI. In other words, even if you set non-zero QPM or TPM values in Serving or AI Gateway, those settings will not override this restriction.&lt;/P&gt;
&lt;P class="p1"&gt;This is expected behavior for certain high-demand hosted models, including GPT-5.x and some Claude variants, when used from &lt;STRONG&gt;trial or Free&lt;/STRONG&gt; Edition workspaces. In those cases, the workspace is often placed in a TRIAL_VERIFIED trust tier, which can block or heavily restrict access to premium models regardless of the limits shown in the UI.&lt;/P&gt;
&lt;P class="p1"&gt;The key point is this: the “rate limit of 0” error is not something that can be fixed by adjusting endpoint settings. It reflects a workspace-level access restriction for that model.&lt;/P&gt;
&lt;P class="p1"&gt;The path forward is one of the following:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;
&lt;P class="p1"&gt;Upgrade the workspace to a paid / fully enabled subscription&lt;/P&gt;
&lt;/LI&gt;
&lt;LI&gt;
&lt;P class="p1"&gt;Work with Databricks Sales or Support to have the workspace converted so it is fully enabled for those premium hosted models&lt;/P&gt;
&lt;/LI&gt;
&lt;/UL&gt;
&lt;P class="p1"&gt;Once the workspace is moved to a PAYABLE_VERIFIED tier, this Databricks-set rate limit of 0 typically disappears, and the same endpoint will often begin working without any additional UI changes.&lt;/P&gt;
&lt;P class="p1"&gt;In the meantime, the practical workaround is to use open-source or otherwise non-gated models, such as Llama, which are not subject to this specific Databricks-imposed 0-rate-limit restriction.&lt;/P&gt;
&lt;P class="p1"&gt;Hope this helps, Louis.&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 13 Mar 2026 12:41:22 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/permission-denied-the-endpoint-is-temporarily-disabled-due-to-a/m-p/150800#M1695</guid>
      <dc:creator>Louis_Frolio</dc:creator>
      <dc:date>2026-03-13T12:41:22Z</dc:date>
    </item>
  </channel>
</rss>

