Anthropic API

Creator

Creator

Seonglae Cho

Created

Created

2024 Aug 17 2:55

Editor

Editor

Seonglae Cho

Edited

Edited

2024 Oct 16 14:42

Refs

Refs

Prompt Caching

Prompt caching with Claude

Prompt caching, which enables developers to cache frequently used context between API calls, is now available on the Anthropic API. With prompt caching, customers can provide Claude with more background knowledge and example outputs—all while reducing costs by up to 90% and latency by up to 85% for long prompts.

Prompt caching with Claude

https://www.anthropic.com/news/prompt-caching

Prompt caching with Claude

OpenAI Prompt Caching in GPT 4o and o1: How Does It Compare To Claude Prompt Caching? - Bind AI

OpenAI recently introduced prompt caching features as a part of its annual DevDay announcements. Prompt caching—which OpenAI claims can benefit users with a 50% discount on inputs—will now applied to various models, including GPT-4o and its mini versions. Unsurprisingly, this has generated excitement among developers, with many already drawing comparisons between OpenAI's and Claude's prompt

OpenAI Prompt Caching in GPT 4o and o1: How Does It Compare To Claude Prompt Caching? - Bind AI

https://blog.getbind.co/2024/10/03/openai-prompt-caching-how-does-it-compare-to-claude-prompt-caching/

OpenAI Prompt Caching in GPT 4o and o1: How Does It Compare To Claude Prompt Caching? - Bind AI

Batch processing

Introducing the Message Batches API

We’re introducing a new Message Batches API—a powerful, cost-effective way to process large volumes of queries asynchronously.

Introducing the Message Batches API

https://www.anthropic.com/news/message-batches-api

Introducing the Message Batches API

prefilling assistant’s answer

Prefill Claude's response for greater output control - Anthropic

Prefill Claude's response for greater output control - Anthropic

https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/prefill-claudes-response

Recommendations

//////