Claude Sonnet 5.5
claude-sonnet
Fast Claude model for everyday coding, agents, and knowledge work
ReasoningTool CallingAttachments
Context Window
1M
Max Output
128K
Temperature
No
Open Weights
No
Knowledge Cutoff
2026-06
Released
2026-09-28
Last Updated
2026-09-28
Modalities
Input:TextImagePDF
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Terminal-Bench | 70.6 | score |
| FrontierCode | 46.2 | score |
| CursorBench | 55.5 | score |
| GDPval-AA | 1844 | Elo |
| Humanity's Last Exam | 64.5 | score |
| OSWorld | 80.1 | partial score |
Available Providers (4)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 LLM Gateway | Rp 35.761 | Rp 178.801 | Rp 3.577 | Rp 44.701 | effort | — |
 Merge Gateway | Rp 35.761 | Rp 178.801 | Rp 1.789 | Rp 44.701 | ✓ | — |
 Eden AI | Rp 35.761 | Rp 178.801 | Rp 1.789 | Rp 44.701 | effort | — |
 CrossModel | Rp 35.761 | Rp 178.801 | Rp 1.789 | Rp 44.701 | effort | — |