AI & ML platforms
KServe Self-Hosted
Explore this developer service’s free allowance, critical restrictions and official documentation before deploying.
Apache-2.0 open-source Kubernetes inference platform for predictive and generative AI models, with standardized inference APIs and optional Knative scale-to-zero; no vendor-imposed model-serving request or seat quota in the self-hosted software.
Plan details
- Plan
- Ongoing free allowance
- Credit card
- Not required
- Commercial use
- Allowed
- Last checked
- 2026-10-26
Important restrictions
You supply and pay for Kubernetes nodes, GPUs/CPUs, storage, network, observability, backups and model downloads; model weights have separate licenses. Knative-based serverless mode requires additional cluster components. No managed inference compute is included.
Independent community listing, not affiliated with the provider. Always check the latest billing policy and quotas before enabling paid usage.