About Serverless Inference
Run inference on CoreWeave without managing infrastructure
Serverless Inference lets you deploy and serve AI models without provisioning or managing the underlying infrastructure. CoreWeave automatically handles scaling, routing, and resource allocation so you can focus on your models.
CoreWeave delivers Serverless Inference through W&B Inference, so the canonical setup, usage, and reference documentation lives in the W&B docs. Read about getting started with Serverless Inference.
Last modified on May 29, 2026