You can find a list of the data transfer and caching rates on the Amazon API Gateway pricing page. There is also a free tier, which includes one million API calls per month for up to 12 months Topics ...

AWS said prompt caching reduces costs “by up to 90% and latency by up to 85% for supported models. ... Anthropic’s Claude 3.5 Sonnet and Haiku offer prompt caching on its API.

But Thatcher later found a second hole in AWS API Gateway that allowed him to use HTTP header-smuggling to sneak phony headers to the back end and employ a cache poisoning attack on the server ...