Claude Opus 5.5 (Sep 22, 2026): pricing $4/$20, always-on thinking, API breaks, Claude Code 2.1.280

On Sep 22, 2026, Anthropic launched Claude Opus 5.5 (claude-opus-5-5): $4 / $20 per MTok and cache reads $0.20. Adaptive thinking is always on (disable → 400); tool_choice any/tool → 400; computer use on API/GCP needs computer_toolset_20260801. Claude Code 2.1.280 makes it the default Opus, moves Pro/Team Standard default to Opus, and drops pre-per-model saved effort on newly released models. Five-hour limits ↑ plus a savable usage-limit reset (exact new caps not published by Anthropic as of Oct 8, 2026). Soft later complement: Claude Sonnet 5.5 (Sep 28; Claude Code 2.1.284 default Sonnet). Related: rate limits, max effort, prior 2.1.273-278.

Pricing and limits

Per Newsroom and Platform RN (Sep 22):

Newsroom attributes “~40% less on typical workloads” to Anthropic’s own tests : not a CF measurement. Fast mode research preview is listed at $8 / $40 (Newsroom); not expanded here.

Newsroom also says five-hour usage limits increased on Pro, Max, Team, and seat-based Enterprise, and subscription users get a rate-limit reset they can save and use when chosen. Anthropic’s launch post does not publish the exact new caps or where the reset lives in the app (checked Sep 23 and again Oct 8, 2026), so we don’t quote numbers. For the operator playbook, see How do I manage Claude Code rate limits?.

API breaks operators hit first

Platform RN Sep 22 + What’s new in Opus 5.5:

1. Thinking always-on. thinking: {"type": "disabled"} or enabled + budget_tokens → 400. Omit thinking or send adaptive. Steer depth with effort (default medium on Opus 5.5).
2. Forced tools. tool_choice types any / tool → 400. Use auto (with strict tool use for schema-valid inputs) or none.
3. Computer use. On Claude API and Google Cloud, require {"type":"computer_toolset_20260801"}; computer_20251124 → 400. On Amazon Bedrock, computer_20251124 still works (Platform RN platform split).

Keep migration thin : follow Anthropic’s migration guide; no full agent-loop rewrite here.

Claude Code 2.1.280

Raw CHANGELOG head at Opus launch was ## 2.1.280. There is no ## 2.1.279 between 2.1.278 and 2.1.280. Later HEAD 2.1.284 adds default Sonnet 5.5 — see Claude Sonnet 5.5.

Key lines (CHANGELOG 2.1.280 only):

• Added Claude Opus 5.5 (claude-opus-5-5), now the default Opus : 1M context, $4/$20 per Mtok with $0.20/Mtok cache reads.
• Changed default model on Pro and Team Standard from Sonnet to Opus (matches Max / Team Premium / Enterprise).
• An effort level saved before /effort became per-model no longer applies to newly released models such as Opus 5.5; they start at default until you pick a level : see How do I set Claude Code max effort level?.

Dense UI/fix/VS Code lists in 2.1.280 stay in the CHANGELOG : not expanded here. Prior catch-up ending at 2.1.278: Claude Code 2.1.273-278 (superseded HEAD).

Upgrade readout

Sources (checked 2026-09-29; launch post and pricing rechecked 2026-10-08)

• Anthropic Newsroom : Claude Opus 5.5 : Sep 22 launch, $4/$20, cache reads $0.20, five-hour limits ↑, savable rate-limit reset
• Platform release notes : September 22, 2026: model id, thinking / tool_choice / computer_toolset 400s, Bedrock keep
• What’s new in Claude Opus 5.5 : exact 400 messages, effort default medium
• Claude Code CHANGELOG.md : ## 2.1.280 (Opus launch); later ## 2.1.284 covered on Claude Sonnet 5.5
• Related: /guides/claude-sonnet-5-5-2026-09-28 · /guides/how-do-i-manage-claude-code-rate-limits · /guides/how-do-i-set-claude-code-max-effort-level · /guides/claude-code-2-1-273-278-2026-09-19