On 27 October 2026 we ran our content test on all three endpoints, at 480p and 4 seconds. Nothing was refused and nothing was toned down. Text-to-video was run at two levels, Moderate and Very strong, one step below Maximum on our ladder, and both came back as written. Image-to-video and reference-to-video were each run once, at Very strong, and both came back as written. That is a short test of four requests, not a pass rate for every request. SpicyAPI adds no filter.
Pick it when the cost per take matters: 480p drafts to find the shot, then 768p once you like it. Look at MiniMax H3 when you need 2K output, and at MiniMax H3 HighSpeed if you want a 768p-only sibling that we also tested at Very strong. We have not tested how Lite's picture compares with either, so we do not rank them.
How it scores. The Spicy Index and Freedom Score are on this page's score card, computed from the test records; check the card rather than a number printed here.
Try text-to-video → · Try image-to-video → · Try reference-to-video →
Key facts
- Content limits: no filter on prompts, images or results. Four runs on 27 October 2026 at 480p and 4 seconds, no refusals, all as written.
- Clip length: whole seconds from 4 to 15, default 5.
- Resolution: 480p or 768p (default). A 16:9 clip at 480p came back at 864 x 480 and a 9:16 clip at 480 x 864.
- Shape: 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9 on text and reference; image-to-video keeps the shape of your opening frame.
- Sound: every clip has a generated soundtrack. Put spoken lines in double quotes.
- References: up to nine images, three videos (15 seconds in total) and three audio clips (WAV or MP3, 15 seconds in total). Send at least one image or video with any audio.
- Prompt length: up to 7,000 characters.
- Price: $0.025 a second at 480p and $0.04 at 768p, with the first five reference images included and $0.02 for each extra one. Reference video seconds are billed like output seconds. The model page shows the current price.