Claude Opus 5.5 - Fable-level work for less than half the price

Canonical version: Claude Opus 5.5 - Fable-level work for less than half the price.

Less than two months after Claude Opus 5, Anthropic just released Claude Opus 5.5. It's the first model of the new Claude 5.5 family, and Sonnet 5.5 and Haiku 5.5 are coming "in the coming weeks".

The pitch fits in one sentence: it performs at the level of Claude Fable 5.1 on most tasks, and costs 40% less to run than Opus 5. Fable 5.1 costs $10/$50 per million tokens. Opus 5.5 costs $4/$20. Do the math...

In this piece, I'll go over what changed for those of us who use Claude every day, what breaks if you build on the API, and one safeguards detail that deserves more attention than it got.

Cheaper, and not just per token

Token prices dropped 20% ($4 input, $20 output), and cache reads dropped 60% to $0.20. But the "40% cheaper" figure comes from somewhere else: the model simply uses fewer tokens and fewer steps to finish the job, and it's more than 30% faster.

The customer numbers all point the same way. Box saw about a third of the tokens Opus 5 used. GitHub says it solved more terminal tasks than Opus 5 in VS Code in less than half the steps. Deloitte got 72% of known bugs caught in code review at the LOWEST effort setting, against 56% for Opus 5 at high effort. Those are internal evals, not independent benchmarks, so take them with a grain of salt. Still, when five different companies report the same pattern, I pay attention.

On Anthropic's benchmarks, it beats Fable 5.1 almost everywhere (66.4% vs 55.8% on Terminal-Bench 4.0, for instance). Anthropic itself says not to read too much into those margins, because a few points don't make a noticeable difference in real work at this level. I really like that honesty. GPT-6 Astra still wins on agentic science and AutomationBench, but Opus 5.5 beats it on FrontierCode at roughly 20% of the per-task cost.

It finally writes clearly

This is my favorite part. The most common complaint about Opus 5 was dense, hard-to-follow output. Opus 5.5 puts the important information first, uses less jargon, and follows the writing rules you give it. Jackson Kernion, who worked on it, says he hasn't been this happy with a model's writing since Opus 4.6.

Dan Shipper's tests at Every back this up partially: the highest reading ease score they've measured, but it still buries the main point in intro paragraphs. So, clearer, not yet a great editor. For me, that's still a big deal. I read Claude's output for hours every day in Claude Code. Less effort per message adds up fast!

What breaks on the API

If you use the API directly, don't just swap the model ID:

• Thinking can't be disabled anymore. Use the effort parameter instead (the default is now medium, it was high on Opus 5)
• Forced tool use (tool_choice of type any or tool) returns an error
• Thinking blocks are tied to the model and the conversation. Keep your conversations append-only
• The old computer_20251124 tool is rejected on the Claude API and Google Cloud

And a silent one: the text the model writes between tool calls now comes back in thinking blocks, empty by default. If your UI shows progress updates, it will go quiet without any error.

The routing detail agent builders should know

Opus 5.5 is comparable to Mythos 5.1 in biology and cybersecurity, so it ships with Fable-class safeguards. When a classifier fires, your request is answered by an OLDER model: Claude Opus 4.8 for most cybersecurity requests, Opus 5 for biology and frontier LLM work.

In a multi-step agent run, that means some steps may be handled by a different, weaker model than the one you selected. Your evals probably assume one model per run. Handle refusals explicitly, and log which model actually answered.

On alignment, Anthropic reports its best score to date, with METR and Frontier Design testing before release. It's also the first model since Dario Amodei called for "pacing the frontier". One caveat Anthropic admits: the model often suspects it's being tested, which makes those results harder to read.

What I'd do

• In Claude Code, Opus 5.5 is already the default for Pro, Max and Team plans, at medium effort. Rate limits go about 25% further than with Opus 5, and the five-hour limits went up. Try medium before reaching for high
• Re-read your CLAUDE.md. A model that follows writing rules more closely will also expose the vague or contradictory ones
• If you pay for Fable 5.1, run your own evals. For most work, Opus 5.5 looks like the better deal
• If you're cost-sensitive, wait a few weeks for Sonnet 5.5 and Haiku 5.5

The full breakdown (benchmarks table, API details, reception) is in my Claude Opus 5.5 note.

That's it for today! ✨

References

• Announcement: https://www.anthropic.com/claude-opus-5-5
• What's new in Claude Opus 5.5 (API docs): https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5
• Launch thread: https://x.com/claudeai/status/2102435511222890900
• The New Stack on safeguard routing: https://thenewstack.io/claude-opus-5-5-release/
• TechCrunch: https://techcrunch.com/2026/09/22/anthropic-releases-opus-5-5-with-lower-prices-and-fable-level-performance/

Related

• Claude Opus 5.5
• Claude Opus 5
• Claude Fable 5.1
• Claude 5
• Claude Code
• Anthropic
• GPT-6 Astra

About Sébastien

Ready to get to the next level?