返回模型列表

KwaiKAT: KAT-Coder-Pro-V2下线

kuaishou/kat-coder-pro-v2
对比对话

KAT-Coder-Pro V2 is theKwaiKAT’s Latest Flagship Agentic Coding Model. Engineered for multi-scaffold generalization, the model is natively compatible with over 10 mainstream AI coding tools—such as Claude Code, Cline, Kilo, and OpenCode, offering unparalleled flexibility. Through dedicated full-pipeline optimization for OpenClaw, KAT-Coder-Pro V2 is trained from the ground up to master complex, real-world application workflows with ease. Beyond logic, KAT-Coder-Pro V2 achieves a breakthrough in frontend aesthetic generation. In Landing Page and PPT scenarios, the model delivers a paradigm shift in user experience: No Structured Spec Needed: Users no longer need to provide rigid design specifications. Simply describe what you want in plain language to receive production-grade, high-quality output that rivals structured design inputs. Mass Market Expansion: This evolution expands the model's service boundary from the 1% of power users to hundreds of millions of ordinary users, truly democratizing professional-grade creation.

由:KwaiKAT输入类型:输出类型:发布时间:2026-03-30

供应商

在多个供应商之间路由请求。复制供应商标识以设置偏好供应商。

供应商缓存命中率上下文
streamlake
-$0.3/ 百万 token$1.2/ 百万 token读取:0.06/ 百万 token写入:-/ 百万 token256K1.15s6.2tps

可用率

AI Gateway 直连请求及各供应商的成功率。

Aug 31, 07:59
Streamlake100.00%

吞吐量

AI Gateway 实时流量的 P50 吞吐量,单位为每秒 token 数(TPS)。

Aug 31, 01:00
Streamlake6.2 tps

延迟

AI Gateway 实时流量的 P50 首 token 延迟(TTFT),单位为毫秒。

Aug 31, 01:00
Streamlake1.15s

活动

该模型随时间变化的 token 用量和请求流量。

Token 消耗
Aug 30
Streamlake2.7K

按实际处理请求的供应商拆分 token 用量。区块越大,表示该供应商处理的模型流量越多。

基准测试

标准化评测得分。百分比越高越好,并展示排名百分位。

指标来源:Artificial Analysis

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token 排行
No data
No app usage is available for this period.