cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results forĀ 
Search instead forĀ 
Did you mean:Ā 
Help
Generative AI
Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results forĀ 
Search instead forĀ 
Did you mean:Ā 

Databricks-hosted Foundation Model APIs blocked by workspace rate limit of 0

APIUser4827
New Contributor

2 weeks ago

Hello,

My Databricks-hosted Foundation Model endpoints appear READY, but every runtime invocation is blocked by a workspace-level quota.

Workspace details:
- Workspace ID: 7474647458172567
- Workspace URL: https://dbc-731cb41b-741e.cloud.databricks.com
- Region: us-west-2
- Serverless compute: enabled

Reproduction:
1. GET /api/2.0/serving-endpoints/databricks-claude-sonnet-5 returns HTTP 200.
2. Endpoint state is READY and config_update is NOT_UPDATING.
3. POST /serving-endpoints/databricks-claude-sonnet-5/invocations returns HTTP 403:
PERMISSION_DENIED: The endpoint is temporarily disabled due to a Databricks-set rate limit of 0.

The same workspace-level rate-limit error has also affected other Databricks-hosted foundation models, so this does not appear to be a missing endpoint or Model Service configuration issue.

Billing has been upgraded from the trial flow and a payment method is present. Partner-powered AI features are enabled. Creating another Model Service does not resolve the problem.

Could a Databricks community engineer please clarify:
1. How can an individual pay-as-you-go workspace receive a non-zero Foundation Model API rate limit?
2. Does the workspace/account need a manual entitlement or verification-tier update?
3. Which billing or account team can remove the Databricks-set rate limit of 0 if standard support is unavailable?

Thank you.

0 Kudos
1 REPLY 1

balajij8
Esteemed Contributor II

2 weeks ago

@APIUser4827 

What you are encountering is the expected behavior in free edition. Databricks imposes a hard limit of 0 on premium, high demand Foundation Models especially - Claude and GPT groups when a workspace is operating under a free edition.

You can use llama 4 maverick or other Llama models without issues for now as they are exempt from this specific zero-rate-limit hold, so you can swap the endpoint configuration to the Maverick model. You can reach out to your Databricks account team or via a ticket for the upgrade as you are already on a paid workspace

0 Kudos
Announcements