GLM-5.3 is Zhipu AI’s next-generation flagship text model, built on GLM-5.2 and enhanced through large-scale, long-horizon task post-training. It delivers an approximately 50% improvement in coding experience, autonomously handling complex project development, debugging, validation, and delivery. It also supports a 1-million-token context window, up to 128K-token outputs, tool calling, and MCP, with strong performance in cybersecurity tasks such as code review and vulnerability detection.
返回模型列表
88.5%$1.4$0/ 百万 token$4.4$0/ 百万 token读取:0.260/ 百万 token写入:-/ 百万 token1M3.47s53.4tps
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
BigModel下线
bigmodel
可用率
24 小时AI Gateway 直连请求及各供应商的成功率。
Aug 25, 07:59
BigModel100.00%
吞吐量
24 小时AI Gateway 实时流量的 P50 吞吐量,单位为每秒 token 数(TPS)。
Aug 25, 07:00
BigModel53.4 tps
延迟
24 小时AI Gateway 实时流量的 P50 首 token 延迟(TTFT),单位为毫秒。
Aug 25, 07:00
BigModel3.47s
活动
该模型随时间变化的 token 用量和请求流量。
Token 消耗
Aug 24
BigModel243.0M
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。
该模型暂无基准测试数据。
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
相关模型
更多模型来自 Z.ai
