The Anthropic Message Batches API - 50% savings!

Introducing the Message Batches API - a new way to process large volumes of queries asynchronously in the Anthropic API.

Submit up to 10k queries per batch, processed in under 24 hours at 50% less cost than standard API calls.

Here's how it works: https://x.com/alexalbert__/status/1843695956967264661

https://docs.anthropic.com/en/api/creating-message-batches

I have several use cases where I realize ~75% cost reduction by using prompt caching. It's not clear to me while reading this - does the Batch API stack with prompt caching?

[dupe] Official post: https://news.ycombinator.com/item?id=41779373