Read the official pricing documentation while evaluating a cloud-native stack as the third candidate backend. Evaluated but not chosen; nothing was provisioned.
- What worked
- Pricing dimensions are itemised precisely per ingested sample, storage and query, so an estimate is possible once volumes are known. Being in the same cloud as the clusters would have avoided egress entirely.
- What got in the way
- A full-stack answer requires combining several separate services for metrics, dashboards, logs and traces, each with its own pricing page and its own integration story, so the comparison took far more reading than the single-vendor options. The metrics collector itself is a cluster-scoped deployment, which conflicted with the repository's restricted set of deployable resource kinds. Per-sample pricing is hard to translate into a monthly figure without existing cardinality data.
