Skip to main content

The Batch API

50 percent off input and output tokens for anything that can wait up to 24 hours.

Hand-drawn line illustration in warm terracotta and cream: two loopy line-drawn hands push a wide cream tray packed with many small cream squares while a third hand pinches a single tiny square, a one-line profile face observing between them.

What it is​

The Message Batches API takes a file of requests instead of one request at a time. Per the platform docs (verify against platform.claude.com/docs; limits and pricing drift): batches run up to 100,000 requests, results arrive within 24 hours and usually much sooner, and both input and output tokens are billed at 50 percent of the standard price. The discount stacks with prompt caching, so a cached, batched input token carries both reductions.

The sorting question​

The Batch API turns one product question into a pricing lever: does this call need an answer while someone is waiting? Interactive chat does. Almost everything else in a real product does not: nightly enrichment, classification backfills, embedding-adjacent preprocessing, eval suite runs, report generation, content pipelines, retroactive re-processing after a prompt improvement. Any of those running on the synchronous API is paying double for latency nobody is experiencing.

The corpus is full of workloads with exactly this shape, whether or not each story names the API surface it bills through: Scribd generates metadata across a corpus of documents at a scale it reports as "70% of content improved with AI-generated metadata" (source), and Local Falcon reports "1 million customer reviews analyzed simultaneously" (source). Bulk, non-interactive, tolerant of hours: the batch profile.

Why it pairs with evals​

The least obvious high-value batch workload is your own eval suite. Anthropic's Demystifying evals for AI agents (January 2026) pushes teams toward evaluating continuously, and eval runs are the perfect batch customer: large, repetitive, cache-friendly, and never blocking a user. Cutting the eval bill in half changes how often a team can afford to run them, which changes how fast the product improves. Eve Legal, for instance, reports "around 420 test suites run against every model the company uses." (source)

The honest boundary​

Batch is a discount on patience, not a workaround for capacity planning. Results within 24 hours is the contract, so anything with a same-hour SLA stays synchronous, and a pipeline that feeds a human's morning review needs to be submitted with the window in mind, the way scheduled, overnight agent work already is.

Further Reading​