claude-batch-toolkit

This is interesting for offloading "tiered" workloads / priority queue with coding agents. If 60% of the work is "edit this file with this content", or "refactor according to this abstraction" then low latency - high token inference seems like a needed improvement. Recently someone made a Claude plugin to offload low-priority work to the Anthropic Batch API [1]. Also I expect both Nvidia and Google to deploy custom silicon for inference [2] 1: https://github.com/s2-streamstore/claude-batch-toolkit/blob/... 2: https://www.tomshardware.com/tech-industry/semiconductors/nv...

Hey HN. I built this because my Anthropic API bills were getting out of hand (spoiler: they remain high even with this, batch is not a magic bullet). I use Claude Code daily for software design and infra work (terraform, code reviews, docs). Many Terminal tabs, many questions. I realised some questions are ok to wait on and with that comes some cost savings. So here is a small MCP that lets you send work directly to Anthropic's Batch API from inside Claude Code, for the same quality responses just 50% cheaper, results come back in ~30min-1hr. How it works: you type /batch review this codebase for security issues, Claude gathers all the context, builds a self-contained prompt, ships it to the Batch API via an MCP server, and you get notified in the status bar when it's done (optional). The README has installation instructions, which