The short answer
The registry records Baseten Production ML Model Serving & GPU Hosting as a possible interpretation of BASETEN* ML DEPLOY. This descriptor-to-company association has not passed claim-level evidence review. Compare the exact line, amount and posted status with your own receipt or account activity; the name alone cannot confirm the merchant or whether you authorized the payment.
What do the parts of BASETEN* ML DEPLOY mean?
- BASETEN * ML DEPLOY
- Before the asterisk, "BASETEN" usually names the platform or parent company. After it, "ML DEPLOY" usually names the product, store or order. How descriptors work →
The notes below are unreviewed registry explanations, not confirmation of merchant identity, authorization or current policy. Claim-level source review is pending for this entry.
Why it shows up like this
Unreviewed registry note: A charge labeled BASETEN* ML DEPLOY on your credit card or banking statement comes from Baseten, Inc. for Baseten Production ML Model Serving & GPU Hosting. Baseten is a cloud infrastructure platform that enables engineering teams to serve machine learning models on dedicated GPU hardware. On billing statements, the transaction commonly appears as BASETEN* ML DEPLOY, BASETEN INC, BASETEN SAN FRANCISCO, or BASETEN.CO.
Unreviewed registry note: Billing on Baseten is usage-based and reflects actual compute consumption. The platform bills per millisecond of model execution or per hour for reserved GPU instances such as NVIDIA A10G or A100 graphics cards. An unexpected invoice often occurs when a model packaged with the Truss framework is deployed to production, an API endpoint receives high web traffic, or a developer leaves a dedicated instance active without enabling scale-to-zero settings.
Unreviewed registry note: To locate the source of the charge, log in to the web console at app.baseten.co. Navigate to Settings and click Billing to inspect your consumption metrics and itemized monthly invoices. If you want to stop ongoing charges immediately, open the Models tab in your dashboard, select each active model, and click Deactivate. Deactivating models removes the provisioned instances and stops future compute billing.
Don’t recognize it? Common scenarios
- Unreviewed registry note: An AI model packaged with Truss was deployed to Baseten's production inference cluster.
- Unreviewed registry note: An autoscaling model endpoint received continuous traffic from an external web app.
- Unreviewed registry note: A dedicated GPU instance remained active on the account.
Frequently Asked Questions
How does Baseten handle scale-to-zero?
Unreviewed registry note: Baseten models configured with autoscaling scale down to zero active instances when idle, incurring no compute costs during inactivity.
Independent reference — not affiliated with Baseten, Inc.. Billing names and policies change; verify with the merchant or your bank before acting.
Sources and evidence
Sources may support different parts of this page. A company homepage does not establish a statement descriptor, refund policy or contact detail. Check the claim notes and your own receipt before acting.
- Baseten Pricing & Dedicated GPU Rates https://www.baseten.co
- CFPB: Disputing Unrecognized Charges https://www.consumerfinance.gov
Evidence review pending · pending · About UnknownCharges