Claude Opus 5.5 vs Claude Sonnet 5.5: price comparison
Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00 (Anthropic list prices, checked 2026-11-12). This page compares cost only; it does not rate quality, so test both on your own task.
Prices and limits
| Claude Opus 5.5 | Claude Sonnet 5.5 | |
|---|---|---|
| Input (per 1M tokens) | $4.00 | $2.00 |
| Output (per 1M tokens) | $20.00 | $10.00 |
| Cache hit (per 1M) | $0.20 (5% of input) | $0.10 (5% of input) |
| 5-minute cache write | $5.00 | $2.50 |
| 1-hour cache write | $8.00 | $4.00 |
| Batch input / output | $2.00 / $10.00 | $1.00 / $5.00 |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Minimum cacheable prompt | 512 tokens | 512 tokens |
| Tokenizer | newer (Opus 4.7 and later) | newer (Opus 4.7 and later) |
Per token, Claude Opus 5.5 input costs 200% of Claude Sonnet 5.5's, and output costs 200%. Sources: Anthropic pricing, models overview.
What typical calls cost
Token counts per call are assumptions (shown in each row); adjust them in the Claude pricing calculator.
| Workload (input / output tokens) | Claude Opus 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Chat assistant turn (2,000 / 500) | $0.01800 | $0.00900 |
| RAG / document Q&A call (8,000 / 400) | $0.04000 | $0.02000 |
| Extraction or classification (1,500 / 150) | $0.00900 | $0.00450 |
| Agent / coding loop step (30,000 / 2,000) | $0.16000 | $0.08000 |
| Long-document summarization (150,000 / 1,500) | $0.63000 | $0.31500 |
| Translation (1,000 / 1,200) | $0.02800 | $0.01400 |
Before you switch
- Run your own evaluation: price differences are certain, quality differences depend on your task.
- Prompt caching and the Batch API change the totals a lot; model them in the prompt caching calculator and the batch API savings calculator.
- Check the API differences for the newer model in Anthropic's migration guides before changing a production setting.
More: all comparisons · LLM API pricing · cost by workload