MiniMax merilis H3 pada 31 Juli. Kombinasinya jarang: perusahaan memberi harga API komersial sekaligus mengatakan bobot model akan dibuka.
H3 menerima teks, gambar, video, dan audio dalam satu konteks. Model ini menghasilkan video hingga 2K, 15 detik, dengan stereo native.
Open weight belum menjadi berkas unduhan
“We plan to open up the model weights in the coming days, subject to applicable laws and regulations.”
Developers still need the license, commercial-use terms, hardware guidance and a technical report before treating H3 as a deployable open model.
Harga membuat posisinya jelas
Shanghai Securities News, The Beijing News and 21st Century Business Herald reported H3 at RMB 0.8 per second for 2K generation, about one-third of comparable flagship video models. A 15-second 2K clip is roughly RMB 12 before platform packaging.
Taruhan teknisnya adalah konteks terpadu
MiniMax describes H3 through Contextual Omni Representation, H3-VAE, H3-Omni Transformer and In-Context Regeneration. The model handles video, audio, images and text as one creative context.
Most source material requires about 100,000 tokens of inference before being distilled to roughly 4,000 tokens on average. H3-VAE provides a 4x gain in effective sequence length, and workload separation lifted training throughput by nearly 30%.
The next checks are whether weights appear, whether the license works for companies, and whether the community can reproduce usable text, motion and audio control on non-official hardware.
Sumber: blog riset resmi MiniMax, Shanghai Securities News, The Beijing News, CocoLoop, 21st Century Business Herald; situs MiniMax digunakan untuk memverifikasi output 2K/15 detik, stereo native, komitmen open weight, harga RMB 0,8 per detik, perbandingan 768p, dan klaim throughput pelatihan hampir 30%.