<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Batches on AI Knowledge Base</title><link>https://learn-ai.blindshot.kz/topics/batches/</link><description>Recent content in Batches on AI Knowledge Base</description><generator>Hugo</generator><language>en-us</language><atom:link href="https://learn-ai.blindshot.kz/topics/batches/index.xml" rel="self" type="application/rss+xml"/><item><title>Batch Processing</title><link>https://learn-ai.blindshot.kz/docs/anthropic/platform/build-with-claude/batch-processing/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://learn-ai.blindshot.kz/docs/anthropic/platform/build-with-claude/batch-processing/</guid><description>&lt;p&gt;Batch processing is the single biggest lever for cutting Claude API costs on non-urgent workloads — it runs requests asynchronously at roughly half the price, which is why it appears in both the cost-optimization and deployment paths. Pay close attention to the 24-hour completion window and the polling and retrieval flow, since batches are not interactive and you design around eventual results. The common pitfall is reaching for batch on latency-sensitive paths where it does not belong. OpenAI offers an equivalent Batch API with a similar discount but a different file-based job format; read the rate-limits page next to see how batch sidesteps per-minute caps.&lt;/p&gt;</description></item></channel></rss>