Claude Sonnet 5
| Maker | Anthropic |
|---|---|
| Family | Claude Sonnet |
| Released | 2026-06-30 |
| Context | 1M |
| Max output | 128K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, pdf → text |
| Input / 1M | $2.00 |
| Output / 1M | $10.00 |
| Cached input / 1M | $0.20 |
| Review call | $0.0766 |
|---|---|
| Reasoning efforts | low, medium, high, xhigh, max |
| Hosts | Anthropic, OpenRouter |
| Model id | claude-sonnet-5 |
CodePanel's benchmark has not run Claude Sonnet 5 as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The newest ranked model in the Claude Sonnet line is Claude Sonnet 5.5. It caught 77% [64%–89%] of the known bugs at rank 1 of 17, with a measured review cost of $0.0571. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0766 on Claude Sonnet 5 and $0.0766 on Claude Sonnet 5.5, so this model's call is about the same as that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Anthropic | claude-sonnet-5 | $2.00 | $10.00 |
Source: Anthropic pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context | Rank | Bugs caught |
|---|---|---|---|---|---|---|
| Claude Sonnet 5.5 | 2026-09-28 | $2.00 | $10.00 | 1M | #1 | 77% |
| Claude Sonnet 4.6 | 2026-02-17 | $3.00 | $15.00 | 1M | – | – |
Same as on Claude Sonnet 5.5.
Updated Oct 23, 2026