MiniMax-M3
#2 in Small & Edge ModelsMinimax · since 2026-06-01 · 60× · last seen Jul 10, 2026
94
Momentum
MiniMax-M3 is an open-weight multimodal language model released by MiniMax on June 1, 2026. It is built on a Mixture-of-Experts architecture with approximately 428 billion total parameters and approximately 23 billion active parameters per forward pass. Its core architectural innovation is MiniMax Sparse Attention (MSA), which replaces standard quadratic attention to enable a 1-million-token context window at drastically reduced compute cost. M3 is the first open-weight model to simultaneously deliver frontier-level coding, a 1M-token context window, and native multimodality (text, image, video).
Momentum trend
11.04.10.07.
Features
| Key-Benchmark (%) | 59,0% auf SWE-Bench Pro |
| Kontextfenster (Token) | 1.048.576 Token (garantiertes Minimum 512.000 Token) |
| Lizenz | MiniMax Community License (nicht-kommerziell standardmäßig, kommerzielle Nutzung erfordert Kennzeichnung „Built with MiniMax M3“ bzw. Genehmigung) |
| Multimodalität | Nativ multimodal: Text-, Bild- und Videoeingabe, Textausgabe |
| Plattform | MiniMax API, MiniMax Code/Agent-Plattform, Token-Pläne; offene Gewichte auf Hugging Face & ModelScope |
| Preis pro 1M Token | $0,60 Input / $2,40 Output (Standardpreis); mit permanentem 50%-Rabatt: $0,30 Input / $1,20 Output |
| Release-Datum | 1. Juni 2026 |