Claude Sonnet 4.5 → Claude Opus 5.5: cost per request on six tasks
Claude Opus 5.5 costs about 73% more than Claude Sonnet 4.5 per request on six common tasks. It costs no more per result that works if its results work first time at least 74% more often than Claude Sonnet 4.5's. Anthropic has announced Claude Sonnet 4.5's API shutdown for 2026-11-30.
List prices per million tokens
| Model | Input | Cached input | Output |
|---|---|---|---|
| Claude Sonnet 4.5 | $3.00 | $0.30 | $15.00 |
| Claude Opus 5.5 | $4.00 | $0.20 | $20.00 |
Prices checked 2026-11-12.
Cost per 1,000 requests
| Task | Claude Sonnet 4.5 | Claude Opus 5.5 | Change | Cheaper per result that works if it works first time at least |
|---|---|---|---|---|
| Support bot answerInstructions, three help-centre passages and the customer's question in; a short answer out. | $13.50 | $23.40 | 73% more | 74% more often than Claude Sonnet 4.5 |
| Invoice field extractionInstructions and one invoice's text in; about 15 fields as JSON out. | $11.25 | $19.50 | 73% more | 74% more often than Claude Sonnet 4.5 |
| Lead scoringScoring rules and one lead's form answers in; a score and a one-line reason out. | $5.10 | $8.84 | 73% more | 74% more often than Claude Sonnet 4.5 |
| Email reply draftInstructions and the email thread so far in; a reply of about 300 words out. | $10.50 | $18.20 | 73% more | 74% more often than Claude Sonnet 4.5 |
| TranslationInstructions and about 500 words of text in; the same text in another language out. | $14.70 | $25.48 | 73% more | 74% more often than Claude Sonnet 4.5 |
| Search re-rankingA search query and 20 result snippets in; the ids of the best five, in order, out. | $12.75 | $22.10 | 73% more | 74% more often than Claude Sonnet 4.5 |
Token counts are typical sizes, not measurements. Claude Opus 5.5 counts more tokens for the same text (×1.30), which the new model's costs include.
Claude Sonnet 4.5 is being shut down
Anthropic has announced Claude Sonnet 4.5's API shutdown for 2026-11-30, with claude-sonnet-5-5 as the replacement (source).
Test it on your own prompt
The model switch test runs your prompt on both models side by side with your own API key, in your browser.