MiniMax H3 is a multimodal video model generating native 2K clips of 4-15 seconds with synchronized audio, driven by text together with reference images, video and audio for consistent characters and voice.
Text-to-video, image-to-video, reference-to-video, first/last frame control and synchronized audio generation.
Released July 31, 2026.
MiniMax H3 is documented as suited for advertising and e-commerce content creation, with examples including film opening titles, product websites, and animated posters. It is also aimed at branding, product design, UI/UX, and gaming use cases. The model is described as useful for producing campaign visuals and commercial content with consistent characters, products, and motion reference across clips. It is also suited to narrative and social-video production, including text-to-video concepts and short promotional clips.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "minimax/h3", "prompt": "A serene timelapse of clouds over a mountain range" }, ).json() gid = job["id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error"): break time.sleep(5) print(res["video"]["url"])
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "minimax/h3", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json(); } while (["completed", "error"].includes(res.status) === false); console.log(res.video.url);
# submit the generation — the response contains the job "id" curl -X POST https://api.aimlapi.com/v2/video/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"minimax/h3","prompt":"A serene timelapse of clouds over a mountain range"}' # then poll until status is "completed" — video.url holds the result curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
Video: $0.169 / second at 2K resolution. Additional $0.052 per generated reference image.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Image-to-Video Arena | 1354 | Human preference Elo from blind pairwise comparisons of videos animated from the same input image, measured independently by Artificial Analysis | Source | September 21, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
MiniMax H3 This page | Native 2K narrative video with synchronized audio and consistent characters | |||
| Long-form narrative video with strong editing and multi-language | ||||
| Video generation | ||||
| Video generation | ||||
| Video generation |
MiniMax H3 takes image, text as input and returns video.
MiniMax H3 became available on July 31, 2026.
MiniMax H3 is priced at $0.169 / sec (2K).
MiniMax H3 is billed per generation — a fixed charge per output rather than by prompt length.
Yes, MiniMax H3 accepts image input as well as a text prompt.
MiniMax H3 was built by MiniMax.
Use minimax/h3 as the model id on AI/ML API.
Yes. MiniMax H3 is served through AI/ML API, so the same key and endpoint format used for other models applies.
MiniMax H3 generates clips between 4 and 15 seconds long.
MiniMax H3 produces native 2K resolution video.
Yes, MiniMax H3 supports text-to-video, first-and-last-frame control, and image or reference-to-video generation.
MiniMax H3 produces synchronized audio alongside its generated video clips.