reflection/beam-1.0-501b-a23b
模型权重Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a 1M-token context window.
Beam targets software engineering, multi-step tool use, and mathematical and scientific reasoning, with an emphasis on token efficiency. It takes text input and produces text output, supports configurable reasoning effort, function calling and structured outputs, and is released under Apache 2.0.
目前无法通过 EU 区域内路由使用。 区域内路由文档
| US$0.25 | US$1.00 | US$0.05 | 0.88s | 357 tps | ||
| US$0.30 | US$1.00 | US$0.04 | 0.36s | 226 tps | ||
| US$0.40 | US$1.20 | US$0.04 | 0.35s | 178 tps | ||
| US$0.40 | US$1.20 | US$0.04 | 0.12s | 446 tps | ||
| US$0.40 | US$1.20 | US$0.04 | 0.24s | 170 tps |
P50,所有提供商中最佳
P50,最佳提供商
当上游提供商发生错误时,如果您的请求筛选条件允许,我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据: 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。
