MiniMax H3 Max (Image-to-Video)

MiniMax H3 Max animates your picture into a 1 to 15 second video with a generated soundtrack, with an optional last frame, from $0.05 a second.

MiniMax H3 Max (Image-to-Video) animates your picture into a 1 to 15 second video with a generated soundtrack. The picture is the first frame and the video takes its shape; add a last frame with end_image_url and the clip ends on it. H3 Max is a post-trained variant of MiniMax's H3 video model, tuned for stronger prompt adherence and better aesthetics. On November 17, 2026 it ranked third on the Artificial Analysis silent image-to-video leaderboard (Elo 1124).

Use it to bring product shots, portraits, illustrations and storyboards to life, or to move from one frame to another. Describe the motion, the camera and the sound in prompt (required). prompt_expansion_mode sets how much effort goes into rewriting a short prompt: disabled, balanced (about a second, the default) or quality (up to about 30 seconds). target_audio replaces the generated soundtrack with your own clip. If a picture shows a real person, use it only with their permission.

Inputs: prompt and image (both required), end_image_url, duration (1-15 seconds, 5 by default), resolution (480P, 768P or 1080P; 768P by default), prompt_expansion_mode, target_audio and seed. Output: video, one MP4 clip, and expanded_prompt, the prompt after expansion when there was one.

Price per second of video you ask for: $0.05 at 480P, $0.08 at 768P and $0.16 at 1080P. The default 5-second clip at 768P costs $0.40; 15 seconds at 1080P cost $2.40. The finished clip can run up to about 0.7 seconds longer than you ask for: the price counts the seconds you ask for.

It needs a picture (for text alone use MiniMax H3 Max (Text-to-Video)), does not keep subjects from several reference pictures (use MiniMax H3 Max (Reference-to-Video)) and does not edit a video.

Price: From $0.05 per second of duration, depending on resolution. One run with default settings costs $0.40.

Run MiniMax H3 Max (Image-to-Video) via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-image-to-video/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Slowly move the camera closer to the lake, preserve its composition","image":"https://flymy.ai/img/models/bytedance-seedance-2-5-image-to-video.jpg","duration":1,"resolution":"480P"}'

API documentation · Create a free account · Pricing

Related models