ListsThe 5 open-source AI video tools that shipped, ranked by impactMiniMax H3
Every SLOP TV News story about MiniMax H3.
ListsThe 5 open-source AI video tools that shipped, ranked by impact
ExplainersMiniMax H3 guide: specs, license and prices, updated weekly
NewsPruna's P-Video-2-Pro lands 11th on the AI video leaderboard
pricing
AI video discounts end today as per-second prices rise
Promotional rates on fal's MiniMax H3 Max Turbo, Higgsfield's Wan 3.0 API and HeyGen Video close with October, and a two-minute 1080p clip climbs from about $6.25 toward $9.60.
Pika H3 Flex
Pika H3 Flex cuts video generation from 50 steps to six
Pika's post-trained MiniMax H3 turns out a 15-second 768p clip in as little as seven seconds of denoising time, and the API starts at a cent a second.
MiniMax H3
MiniMax H3's 2K finish is now an open 3-step pass
The refiner and decoder still carry MiniMax's H3 license, which excludes the United States, the European Union, the United Kingdom and South Korea.
Utopai Studios
Utopai Studios raises $60M at $1B, The Information reports
The Mountain View studio is fielding offers that could value it at up to $3 billion, and it plans three feature films in theaters in 2027.
MiniMax H3
MiniMax H3 cuts sampling to 4 steps with two open releases
FastH3 Omni ships as an 8-step ComfyUI student; Taobao's PTD LoRAs reach 4 steps, and neither release has independent quality benchmarks.
AI video pricing
The 8 cheapest AI video models per second, from $0.015
Ranked on each vendor's own published list rate, read 22 October 2026: Pruna's reference model leads at $0.015 a second, and Google's Veo 3.1 prices have already gone.
Kling 4.0
Omni reference: what AI video models now take as input
Kling 4.0 takes up to 15 reference assets in one generation, while MiniMax H3 and the open FastH3 Omni cap a request at 12 files.
solarrenderer
SolarRenderer turns game-engine block-outs into video in 4 steps
The team froze a 33B MiniMax-H3 video model, added two small LoRAs, and cut sampling from 50 steps to four, with a streaming variant at 768p.
minimax-h3
MiniMax H3's open license excludes the US, UK and EU
Builds keep appearing under it, including one from NVIDIA Research, while a rival open video model ships with no territory clause at all.
Pruna
Pruna's P-Video-2-Pro-Reference starts at $0.015 a second
Built on MiniMax H3, the model takes up to 9 images, 3 videos and 3 audio files as references, which Pruna bills separately from the output.
FastH3-Omni
FastH3-Omni adds reference images and audio to MiniMax H3
The open-weight model previews on the Reactor API through October 20, when FastVideo says the final weights and training code ship.
Kandinsky 6.0
6 open-weight AI video models that make sound, ranked by GPU
Kandinsky 6.0 Video leads because its 3B Lite model runs on a consumer card, while Prism needs four 80 GB GPUs for its native 2K mode.
Code Video Model
Microsoft's Code Video Model plans shots in code first
The research system writes each shot as a Three.js program, previews it as a low-poly proxy, then has the frozen MiniMax-H3 model render the final clip without retraining.
Seedance 2.5
Seedance 2.5 tops an AI video physics test at 57.76 out of 100
A new benchmark ran 40 controlled physics tasks across eight video models and 1,280 clips, and only one model in the set is closed.
MiniMax H3
How to run MiniMax H3 on a single 12GB graphics card
ComfyUI's repackaged weights cut MiniMax H3 from 123.6GB to 42.5GB, but the local build leaves out the hosted 2K stage behind Hailuo's showreels.
Protoface
Protoface opens its API to 40+ models from $0.003 a second
The platform puts Kling 3.0 Pro, Seedance 2.5, Wan 3.0, Google's Veo 3.1 and Runway Gen-4 Turbo behind one pay-as-you-go key.
FreeVideo
How to run MiniMax H3 on an 8 GB graphics card
FlashML-org's FreeVideo runs an eight-step MiniMax H3 derivative on small cards by streaming weights between GPU, RAM and disk.