Claude Sonnet 5.5 ships at Sonnet 5's price, and the first independent number puts it #3 among reasoning models

Claude Sonnet 5.5 is live. Our sweep read the id claude-sonnet-5-5 at 17:54:45 UTC on September 28 and the alert went out at 17:55:45, 60 seconds later, to 314 inboxes and one phone. OpenRouter listed it nine minutes after that.

THE PRICE DID NOT MOVE

$2 per million input tokens and $10 per million output, the same sticker as Sonnet 5. Cache reads are $0.20 per million; cache writes are $2.50 per million for five minutes and $4 for an hour. Anthropic's claim is that it needs far fewer tokens for the same work, "up to 30% less per task than its predecessor" in its own testing, and that it generates output more than 30% faster than Sonnet 5, its fastest Sonnet yet. Those are the vendor's figures, and we report them as that.

THE FIRST INDEPENDENT NUMBER

Artificial Analysis scores it 56 on its Intelligence Index at max effort, #3 of the 216 reasoning models that index ranks together when we read it on launch day (Artificial Analysis compares reasoning models only with each other). That is a third-party figure, and it is the one to lean on before anybody's launch table, Anthropic's included.

WHAT IT IS

1M-token context, 128K maximum output, reliable knowledge cutoff June 2026, per Anthropic's model docs. The default effort is Medium in Claude Code and the Claude apps and High on the API. It is claude-sonnet-5-5 on the Anthropic API and is on AWS, Google Cloud and Microsoft Azure from day one. Anthropic has committed to not retiring it before September 28, 2027.

WHAT COMES NEXT

Claude Haiku 5.5 "will join the Claude 5.5 family in the coming weeks", Anthropic says, with no date. It is armed on our radar, and so is whichever Sonnet follows this one.