Compare
Claude Sonnet 4.6 vs Claude Sonnet 5
Same two models, priced on three workload shapes. The rate card rarely decides this on its own — the ratio of input to output tokens usually does.
Per million tokens
Claude Sonnet 4.6
Claude Sonnet 5
Monthly cost by workload
Chat assistant
60,000 requests · 1,200 in / 400 out · 30% cached — short prompts, short answers, high volume
Claude Sonnet 4.6
$517.68
Claude Sonnet 5
$347.28
Claude Sonnet 5 is 1.5× cheaper on this shape — $170.40 a month.
RAG over documents
20,000 requests · 18,000 in / 700 out · 75% cached — large retrieved context, heavily cached prefix
Claude Sonnet 4.6
$561.00
Claude Sonnet 5
$401.00
Claude Sonnet 5 is 1.4× cheaper on this shape — $160.00 a month.
Coding agent
4,000 requests · 45,000 in / 6,000 out · 80% cached — long tool-calling loops, big cached prefix
Claude Sonnet 4.6
$511.20
Claude Sonnet 5
$355.20
Claude Sonnet 5 is 1.4× cheaper on this shape — $156.00 a month.