MiniMax API Models

Explore MiniMax text and video models currently public on Infistar and their declared endpoints.

Currently public models

10 models
  • MiniMax-M3.1-FlashFrom Input ¥0.2143 / Output ¥0.8572 per 1M tokens, cache read ¥0.0215
  • MiniMax-M3From Input ¥0.3537 / Output ¥1.4145 per 1M tokens, cache read ¥0.0708
  • MiniMax-H3From ¥0.1631 / second (768p)
  • MiniMax-M2.1-highspeedFrom Input ¥4.2 / Output ¥16.8 per 1M tokens, cache read ¥0.21
  • MiniMax-M2.7From Input ¥2.1 / Output ¥8.4 per 1M tokens, cache read ¥0.42
  • MiniMax-M2.7-highspeedFrom Input ¥4.2 / Output ¥16.8 per 1M tokens, cache read ¥0.42
  • MiniMax-M2.5From Input ¥1.789 / Output ¥7.1562 per 1M tokens, cache read ¥0.1791
  • MiniMax-M2.5-highspeedFrom Input ¥4.2 / Output ¥16.8 per 1M tokens, cache read ¥0.21
  • MiniMax-M2.1From Input ¥2.1 / Output ¥8.4 per 1M tokens, cache read ¥0.21
  • MiniMax-M2From Input ¥2.1 / Output ¥8.4 per 1M tokens, cache read ¥0.21