Zhipu GLM API Models

Explore Zhipu GLM text, embedding, and reranking models currently public on Infistar.

Currently public models

19 models
  • glm-5.3From Input ¥0.4159 / Output ¥0.7625 per 1M tokens, cache read ¥0.0403
  • glm-5.3-flashFrom Input ¥0.0951 / Output ¥0.1902 per 1M tokens, cache read ¥0.0143
  • glm-5.3-flashxFrom Input ¥1.3334 / Output ¥4.6667 per 1M tokens, cache read ¥0.38
  • glm-5.2From Input ¥1.7143 / Output ¥6 per 1M tokens, cache read ¥0.4286
  • glm-5.1From Input ¥3.6267 / Output ¥14.4978 per 1M tokens, cache read ¥0.7841
  • glm-5-turboFrom Input ¥3 / Output ¥13.2 per 1M tokens, cache read ¥0.72
  • glm-5From Input ¥2.4 / Output ¥10.8 per 1M tokens, cache read ¥0.6
  • glm-4.7From Input ¥1.2089 / Output ¥4.8312 per 1M tokens, cache read ¥0.2409
  • glm-4.7-flashxFrom Input ¥0.5 / Output ¥3 per 1M tokens, cache read ¥0.1
  • glm-4.7-flashFrom Input ¥0 / Output ¥0 per 1M tokens, cache read ¥0
  • glm-4.6From Input ¥2.628 / Output ¥9.636 per 1M tokens, cache read ¥0.4818
  • glm-4.5-airxFrom Input ¥7.354 / Output ¥30.0844 per 1M tokens, cache read ¥7.354
  • glm-4.5-airFrom Input ¥0.4818 / Output ¥1.2089 per 1M tokens, cache read ¥0.0964
  • glm-4.5From Input ¥2.628 / Output ¥9.636 per 1M tokens, cache read ¥0.4818
  • glm-4.5-xFrom Input ¥14.708 / Output ¥59.5003 per 1M tokens, cache read ¥14.708
  • glm-4.5-flashFrom Input ¥0 / Output ¥0 per 1M tokens, cache read ¥0
  • embedding-3From Input ¥0.5 / Output ¥0.5 per 1M tokens, cache read ¥0.5
  • embedding-2From Input ¥0.5 / Output ¥0.5 per 1M tokens, cache read ¥0.5
  • rerankFrom Input ¥0.8 / Output ¥0.8 per 1M tokens, cache read ¥0.8