MiniMax video model generates a 15-second clip in 13 seconds, enabling infinite interactive AI live streams such as infiniteslop.ai and foul.live.
MiniMax real-time video model
by MiniMax
MiniMax video model reportedly fast enough to generate 15-second clips in about 13 seconds, used for live AI streams.
Updated EU status checked Last shown
MiniMax real-time video model at a glance
- What is MiniMax real-time video model?
- MiniMax real-time video model is a model from MiniMax. MiniMax video model reportedly fast enough to generate 15-second clips in about 13 seconds, used for live AI streams.
- Who makes MiniMax real-time video model?
- MiniMax real-time video model is made by MiniMax.
- Does MiniMax real-time video model work in the EU?
- Unverified. No explicit evidence found. Last verified 14 Nov 2026.
- How much does MiniMax real-time video model cost?
- Pricing unknown. No pricing found for this specific model; MiniMax offers an API platform.
- Where was MiniMax real-time video model shown?
- In 1 creator video by Matt Wolfe. Most recently by Matt Wolfe on 4 Sept 2026, at 18:46 in “AI News: The Most Insane Week So Far This Year!”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
This entry covers a MiniMax video generation model described by creators as running in real time or faster. According to a Matt Wolfe news roundup, it generates a 15-second clip in about 13 seconds. That speed allows continuously generated, interactive AI live streams, with infiniteslop.ai and foul.live named as examples.
MiniMax is a Chinese AI company that develops text, image, speech, music and video models and offers them through its own products and an open developer platform. Its site lists a video model line (MiniMax H3) among its flagship models, described as open. The pages fetched do not confirm which exact model powers the live-stream demos, so the specific model name, version and release date are not verified here.
Access is presumably through the MiniMax platform and API. No pricing, licence terms or technical specifications for this particular real-time model were found in the provided material.
- Reported generation of a 15-second clip in about 13 seconds
- Enables continuous, interactive AI live streams
- Used in demos such as infiniteslop.ai and foul.live
- Part of MiniMax's multimodal model family
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
MiniMax H3
Model · MiniMax
Open-weight video generation model from MiniMax, part of its H3 family alongside H3 Image.
H3 Max
API · fal
Fine-tuned, low-latency variant of MiniMax H3 video model served through fal's paid API.
FastH3
Model · Hao AI Lab
Open-weight 4-step sparse-distilled version of MiniMax H3 for fast text-to-video-and-audio generation on Blackwell GPUs.
Wan3.0
Model · Alibaba
Alibaba's Wan video generation model, reported to produce clips up to about 30 seconds, available via the Wan platform.
MiniMax H3 Image
Model · MiniMax
Open-weights MiniMax image generation and editing model producing up to ~16 MP images in 6 sampling steps.
Gemini Omni 1.2 Flash
Model · Google
Google's video generation model producing clips up to 15 seconds from text, image, video or audio input.