Premium pay-as-you-go account still blocked by Databricks-set rate limit of 0

[LeMi-1]

Hello,

I’m having an issue using the Databricks Foundation Model API.

My account is on the Premium plan, I have a valid payment method attached, and I currently have trial credits available. However, when I try to use the GLM Foundation Model endpoint, every request returns:

403 PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0.

I understand from previous Databricks Community answers that this can happen when a workspace remains in the TRIAL_VERIFIED trust tier, and that adding a payment method does not necessarily move the workspace to PAYABLE_VERIFIED.

I already contacted Databricks Support (ticket #01003452), but they closed the ticket because I do not have a separate support package and recommended that I ask here instead.

This is a personal Premium pay-as-you-go account, not a company/enterprise account.

Could a Databricks employee or community engineer please help clarify:

1. Is my workspace likely still in the TRIAL_VERIFIED trust tier?
2. How can an individual Premium pay-as-you-go customer get moved to PAYABLE_VERIFIED?
3. Who can remove the Databricks-set rate limit of 0 if standard Support cannot help?
4. Is there anything I can do from the Account Console to enable the GLM Foundation Model API?

Thank you.

[DoTA]

A community reply cannot lift the limit - that trust-tier change is Databricks-side only - but a few things that may help.

What is happening: pay-per-token Foundation Model endpoints are gated to PAYABLE_VERIFIED workspaces. Attaching a card does not always flip the tier right away; it typically moves after the account clears identity verification and has had at least one settled billing cycle of real (non-credit) usage. Trial credits alone do not satisfy the "payable" gate, so you stay on TRIAL_VERIFIED and every pay-per-token endpoint shows a rate limit of 0.

Workarounds that do not depend on the tier change:

- External model endpoint. Register your own OpenAI / Anthropic / Google API key as a served entity in Model Serving. You still call the unified /serving-endpoints API and get the AI Gateway features (rate limits, usage tracking), but billing goes to that provider rather than through the gated Databricks pay-per-token path. This works on any tier.

- Provisioned throughput endpoint instead of pay-per-token, if you specifically need an open model hosted on Databricks. You pay for allocated capacity directly, and it is a different path from the pay-per-token trust-tier gate. More expensive at low volume, but usable today.

- If you need GLM specifically, check whether the pay-per-token GLM endpoint is even offered in your workspace region - availability varies by region and an unavailable model can also surface as a 0 limit.

Escalation: since standard Support closed it, the route that tends to work is Account Console > Contact us / billing support (billing questions are handled without a support contract), or your Databricks account rep if you have one. It is also worth tagging a community moderator here - trust-tier tickets can sometimes be routed internally from the forum.