#anthropicapi — Public Fediverse posts

I added prompt caching to my Anthropic Batch API workflow. The hit rate was 0%.

Each model has a minimum cacheable token count — 4,096 for Haiku 4.5. If your cache_control block is below that, the API silently ignores it. Successful response, zero cache reads, no warning.

My IAB taxonomy prompt was 1,064 tokens. Well under the threshold.

Full write-up:

https://mikenoe.com/posts/prompt-caching-classivore/

#AnthropicAPI #LLM #PromptCaching #AIEngineering

💼 Early adopters ThomsonReuters saw improved accuracy in their #CoCounsel platform, while #Endex reduced hallucinations from 10% to 0%

🚀 Now available for #Claude35 Sonnet and Haiku on #AnthropicAPI and @GoogleCloud Vertex #AI