Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.
发布日期2025年9月29日
参数规模—
上下文长度1.0M
许可证Proprietary
知识截止2025年1月31日
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| MMMLU | language reasoning math general | 89.1 | 来源 |
| AIME 2025 | math reasoning | 87.0 | 来源 |
| TAU-bench Retail | reasoning communication | 86.2 | 来源 |
| GPQA | reasoning general | 83.4 | 来源 |
| MMMUval | vision general reasoning multimodal | 77.8 | 来源 |
| SWE-bench Verified (Agentic Coding) | reasoning code | 77.2 | 来源 |
| TAU-bench Airline | reasoning communication | 70.0 | 来源 |
| OSWorld | multimodal general vision | 61.4 | 来源 |
| Terminal-Bench | reasoning code | 50.0 | 来源 |
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| QiHang | $0.43 | $2.14 | 200K | — | — | ✓ | ✗ | ✗ |
| Jiekou.AI | $2.70 | $13.50 | 200K | — | — | ✓ | ✗ | ✗ |
| NanoGPT | $2.99 | $14.99 | 1.0M | — | — | ✓ | ✗ | ✗ |
| 302.AI | $3.00 | $15.00 | 200K | — | — | ✓ | ✗ | ✗ |
| Abacus | $3.00 | $15.00 | 200K | — | — | ✓ | ✗ | ✗ |
| Anthropic | $3.00 | $15.00 | 1.0M | — | — | ✓ | ✗ | ✗ |
| Helicone | $3.00 | $15.00 | 200K | — | — | ✓ | ✗ | ✗ |
| LLM Gateway | $3.00 | $15.00 | 200K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。