Anthropic: Claude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Everything else
| Max output | 128K |
|---|---|
| Input / 1M | $2 |
| Output / 1M | $10 |
| Cache read / 1M | $0.2 |
| Cache write / 1M | $2.50 |
| 1M in + 1M out | $12 |
| Takes | text, image, file |
| Returns | text |
| Tools | yes |
| Reasoning | optional · max, xhigh, high, medium, low |
| Open weights | no |
| Released | 2026-06-30 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | anthropic/claude-sonnet-5 |
Benchmarks
| source | epoch |
|---|---|
| eci | 153.47 |
| confidence | Confident |
| accessibility | API access |
| gpqa | 0.905 |
| gpqaStderr | 0.0178 |
| aime | 0.947 |
| aimeStderr | 0.0226 |
| simpleQA | 0.25 |
| simpleQAStderr | 0.0137 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.