Moving to Sonnet 5.5? Four requests that now return a 400
Same price as Sonnet 5, faster, and better at agentic coding by Anthropic's numbers. But the API breaks in ways a model-ID swap won't catch.
4 min read
Claude
A separate evaluator agent is what makes long agent runs worth the money
Anthropic's harness splits planning, building and testing across agents. The cost jump was 20x, and the reasons it paid off are specific.
3 min read
Claude Opus 5.5 costs 20% less per token and Anthropic says it codes better
The numbers behind the release, what changes in practice, and why Anthropic's own benchmark caveat is worth reading.
3 min read