The cost to store a static set of 400k 768-dimension vectors is also $1 a month on Datastax's AstraDB. However, for that $1, AstraDB replicates the data 3x instead of storing it on a single machine.

Here is a link to the cost calculator. Note that the calculator includes cost of ingestion, but the article only mentions storage costs, not ingestion costs: https://www.datastax.com/pricing/vector-search?cloudProvider...

Disclaimer: I work on vectorsearch/AstraDB at DataStax.

It's hard to compare the cost with the Serverless pricing model, as write and read have extra costs. On the pricing page, datastax costs $4000 to write 100M 768-dim vectors. And 10M query will cost $300, which is only 4 QPS. As comparison, VectorChord can achieve 100 QPS on $250 instance.

The pricing estimator is fake, the bill is real : ).