RunPod
On-demand serverless GPU cloud (A100, H100, RTX series) with autoscaling and per-second billing. The go-to choice for indie AI developers and teams that need GPU compute without committing to AWS or GCP reserved instances.
Baseten
Baseten lets you deploy custom and fine-tuned models as scalable inference APIs with minimal DevOps overhead. It handles GPU provisioning, auto-scaling, and traffic management, making it ideal for teams that need custom model serving beyond off-the-shelf providers.