Message Batches API

API

Definition

An asynchronous Claude API for processing multiple requests in a batch with 50% cost savings versus synchronous requests. Processing takes up to 24 hours with no guaranteed latency SLA. Does not support iterative tool use, streaming, or prompt caching. Best for scheduled, non-blocking analysis.

Example Usage

Use batch API for overnight report generation across thousands of records; use synchronous API for blocking pre-merge PR checks.

Related Concepts

Batch Processing Strategy & API Selection

Prompt Engineering

Batch API saves 50% but has up to 24-hour processing with no latency SLA

Batch Cost Optimization Strategies

Prompt Engineering

50% batch savings are reduced by resubmission costs -- maximize first-pass success

Related Terms

custom_id Streaming

← Back to Glossary