Claude Opus 4
claude-opus
Flagship Claude model for deep reasoning, coding, and long-horizon agents
ReasoningTool CallingAttachments
Context Window
200K
Max Output
32K
Temperature
Yes
Open Weights
No
Knowledge Cutoff
2025-03-31
Released
2025-05-22
Last Updated
2025-05-22
Modalities
Input:TextImagePDF
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Aider Polyglot | 72 | percent correct |
Available Providers (1)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
| Rp 270.506 | Rp 1.352.528 | Rp 27.051 | Rp 338.132 | toggle, budget_tokens | — |