Modal vs Oblivus

Run Python functions on NVIDIA GPUs without provisioning instances; cold starts in seconds

Pay for actual GPU runtime at sub-minute granularity, with scale-to-zero by default

Define environments in code, with automatic image building and caching

From T4 and L4 through A100, L40S, H100, H200 and B200

Per-GPU rates published for each instance type, with multi-GPU pricing scaling linearly

H100 SXM5, NVLink and PCIe SKUs published separately for tradeoffs in interconnect

Significant savings versus on-demand for longer-term commitments