Claude✓ ReviewedAnnounced 22 September 2026Reviewed 25 September 2026Claude Opus 5.5 costs 40% less than Opus 5 and Anthropic says it matches Fable 5.1. Four things break on the way.
Anthropic released Claude Opus 5.5 on 22 September 2026 as its current model for long-running agentic coding and knowledge work, at $4/$20 per million tokens against Opus 5's $5/$25. Anthropic says it performs at Claude Fable 5.1's level on most work while costing 40% less than Opus 5 to run. Opus 5 is now listed among Anthropic's legacy models, and four changes break code written for it, the largest being that thinking can no longer be disabled.
What changed
Anthropic released Claude Opus 5.5 on 22 September 2026, priced at $4 per million input tokens and $20 per million output tokens, both lower than Opus 5's $5/$25, with cache reads at $0.20 per million tokens against Opus 5's $0.50. It keeps Opus 5's one-million-token context window and 128,000-token max output, defaults to medium effort with adaptive thinking always on, and carries a June 2026 knowledge cutoff. Anthropic says it performs at Claude Fable 5.1's level on most work for roughly 40% less than Opus 5 costs to run. Four changes break code already running on Opus 5: thinking can no longer be disabled, forced tool use returns an error, thinking blocks are now tied to the model and the conversation that produced them, and on the Claude API and Google Cloud the earlier computer_20251124 computer-use tool is not accepted. Claude Opus 5 now sits alongside Opus 4.8 among Anthropic's legacy models, still available on every platform that carried it but no longer the model Anthropic recommends starting with.
Why it matters
A lower price and a favourable comparison to the most expensive model in the lineup both invite an automatic upgrade, but the breaking changes are real: an integration built around Opus 5's off-by-default thinking, forced tool use or portable thinking blocks does not migrate cleanly. The saving and the capability claim are worth testing on your own task before treating this as a drop-in replacement.
Bit’s takeaway
The human take
A person tests the four breaking changes on a real integration before trusting the price and capability comparison, and reads the actual bill rather than the headline saving.
Turn this into a workflow
Do not just read the change. Try it safely.
Bit starts from this reviewed update and helps you build a safe way to use it on your own work: what AI can prepare, what you still check, and where the workflow should stop.
Turn this into a safe workflow with BitSources and method