Runpod Serverless Flex pricing: why VRAM alone is the wrong comparison
Runpod's Flex tiers range from $0.58/hour 16GB classes to high-end B300 capacity. The useful decision is model fit, hardware class, and measured cost per job—not VRAM alone.
Runpod Serverless Flex lists the 24GB PRO tier, represented by RTX 4090-class hardware, at $1.10 per GPU-hour with per-second billing. It targets higher-throughput small-to-medium model inference than the standard 24GB class. Worker time is billable during startup, execution and idle windows, even when jobs fail or time out.
Secondary price terms only; primary pricing stays in the deal summary.
Use-case fit and limitations from the existing resource record.
Higher price than the standard 24GB tier; value depends on whether the workload benefits from RTX 4090-class throughput. Failed/timed-out/retried jobs and worker startup/idle time can incur GPU-second charges.
Available
Decision visuals remain traceable to the existing source and verification record.
Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.