#prompt-cache

The latest AI and developer news about #prompt-cache, with the original source and a short summary.

KB Securities Cuts Tokens by 35.9% and Costs by 15.8% Using Amazon Bedrock-Based Context Tier-Routing

Cloud API costs were reduced by 15.8% through a policy that minimizes model switching.

·2·2026.11.12 14:00

Maximizing Claude Code Session Value Through Context and Cache Management

Using /clear between tasks and @-mentioning files helps manage context, while careful model and effort selection preserves prompt cache to reduce token costs.

·2·2026.08.14 09:00

Anthropic lowered the cache TTL on March 6

An analysis suggests that Claude Code's cache TTL changed from 1 hour to 5 minutes.

·1·2026.04.12 14:00