MiniMax-M3 An open-weight MiniMax model for million-token context, coding, and multimodal agent workflows. | MiniMax-M3 | 2026-06-01 | OpenRouter listed | Official · 2026-06-01: $0.3 / $1.2 OpenRouter · 2026-08-11: $0.3 / $1.2 input / output, per 1M tokens | No reliable public source | 1 community discussion / 1 activity snapshot |
MiniMax-M3-MXFP8 The first-party MXFP8-quantized MiniMax-M3 open checkpoint for local multimodal, coding, and agent inference. | MiniMax-M3-MXFP8 | 2026-06-12 | Not separately listed on OpenRouter | No reliable public source | No reliable public source | 1 community discussion / 1 activity snapshot |
M2-her MiniMax text model for role dialogue and persistent persona interactions. | M2-her | Not disclosed | OpenRouter listed | OpenRouter · 2026-08-11: $0.3 / $1.2 input / output, per 1M tokens | No reliable public source | No reliable public source |
image-01 MiniMax's current image generation and editing API model. | image-01 | Not disclosed | Not separately listed on OpenRouter | No reliable public source | No reliable public source | No reliable public source |
Music-2.6 MiniMax's current music model for generating songs up to five minutes. | Music-2.6 | 2026-04-01 | Not separately listed on OpenRouter | No reliable public source | No reliable public source | No reliable public source |
MiniMax-Hailuo-2.3-Fast The fast Hailuo 2.3 endpoint for image-to-video generation. | MiniMax-Hailuo-2.3-Fast | Not disclosed | Not separately listed on OpenRouter | No reliable public source | No reliable public source | No reliable public source |
MiniMax M2.7 MiniMax M2.7 series from MiniMax model release notes. | MiniMax M2.7 | 2026-03-18 | OpenRouter listed | OpenRouter · 2026-08-11: $0.3 / $1.2 input / output, per 1M tokens | LMArena 4 rows | 1 activity snapshot |
MiniMax M2.5 MiniMax M2.5 series. | MiniMax M2.5 | Not disclosed | OpenRouter listed | OpenRouter · 2026-08-11: $0.22 / $0.9 input / output, per 1M tokens | LMArena 3 rows | 1 activity snapshot |
MiniMax-Hailuo-2.3 MiniMax-Hailuo-2.3 video generation model. | MiniMax-Hailuo-2.3 | 2025-10-28 | Not separately listed on OpenRouter | No reliable public source | LMArena 1 row | No reliable public source |
Speech-2.8 MiniMax Speech-2.8 speech generation model. | Speech-2.8 | 2026-01-23 | Not separately listed on OpenRouter | No reliable public source | No reliable public source | No reliable public source |
MiniMax H3 MiniMax H3 is a general-purpose multimodal generation model that understands text, image, video, and audio context and generates native-stereo video up to 2K and 15 seconds. | MiniMax H3 | 2026-07-31 | Not separately listed on OpenRouter | No reliable public source | No reliable public source | 1 activity snapshot |
Music-3.0 MiniMax's July 2026 Music-3.0 music-generation API model. | music-3.0 | 2026-07-16 | Not separately listed on OpenRouter | No reliable public source | No reliable public source | No reliable public source |