Sonnet 5.5 nears Opus 5.5 on agentic tasks but uses about 193k output tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per task, the highest measured, so real cost is $7.60 per task despite unchanged pricing.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
