Side-by-side technical and economic comparison between Anthropic's Claude Opus 5 and Anthropic's Claude Sonnet 5.
| Metric | Claude Opus 5 | Claude Sonnet 5 | Advantage |
|---|---|---|---|
| Provider Organization | Anthropic | Anthropic | — |
| Standard Input / 1M | $5.00 | $2.00 | Claude Sonnet 5 (60% lower) |
| Cached Input / 1M | $0.50 | $0.20 | Claude Sonnet 5 lower |
| Output / 1M | $25.00 | $10.00 | Claude Sonnet 5 lower |
| Context Window | 1M | 1M | Equal |
| Max Generation Tokens | 16.4k | 16.4k | Claude Opus 5 |
| Tokenizer Family | Anthropic Claude BPE (~65k vocabulary) | Anthropic Claude BPE (~65k vocabulary) | — |
| Workload (per month) | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| Chatbot10k requests · 500 in / 200 out | $75.00 | $30.00 |
| RAG app100k requests · 8,000 in / 1,200 out | $7,000.00 | $2,800.00 |
| Coding agent100k requests · 12,000 in / 2,000 out | $11,000.00 | $4,400.00 |
Standard rates, no caching or batch discounts. Model your own numbers below.
Opt for Claude Opus 5 when your engineering requirements prioritize Anthropic's ecosystem, specific tokenizer efficiencies (Calibrated Claude Tokenizer (±3%)), or when your expected prompt-to-completion ratios favor its $5/M input rate.
Opt for Claude Sonnet 5 when looking for Anthropic's tooling integration, specific context window depth (1M tokens), or when output generation volume favors its $10/M rate.
At a typical 3:1 input-to-output token mix, Claude Sonnet 5 is about 60% cheaper than Claude Opus 5. Claude Opus 5 costs $5 per 1M input and $25 per 1M output tokens; Claude Sonnet 5 costs $2 and $10.
Both models have a 1M-token context window.
Claude Opus 5: yes, cached input costs $0.5/1M. Claude Sonnet 5: yes, cached input costs $0.2/1M.