S3 automatically scales to handle very high request rates with typical latencies of 100–200 ms.
- Per prefix throughput: 3,500 PUT/COPY/POST/DELETE and 5,500 GET/HEAD requests/sec.
- No limit on prefixes — distributing requests across multiple prefixes increases aggregate throughput.
Example: 4 distinct prefixes × 5,500 GET/sec = 22,000 GET/sec total.