Text to video
Elo with audio · text-to-video arena
Custom pricing for production workloads
MiniMax H3: native 2K video generation, 4-15s clips with synchronized audio, driven by text, image, video and audio references.
MiniMax H3 is a video generation model with text and reference media inputs, synchronized audio, and controls for first and last frames.
minimax/h3POST https://api.aimlapi.com/v2/video/generationsMiniMax 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.
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.
Human-preference results for MiniMax H3 in text to video, silent video and image to video, next to models available on AI/ML API. Data retrieved Nov 4, 2026.
Elo with audio · text-to-video arena
Elo · silent text-to-video arena
Elo with audio · image-to-video arena
Arena results for models you can call with the same API key.
Blind votes on clips with generated sound, made from a text prompt. MiniMax H3 ranks #3 of 31.
The same text-to-video task, judged as silent video. MiniMax H3 ranks #6 of 36.
Blind votes on clips with sound animated from a start image. MiniMax H3 ranks #4 of 29.
Clips animated from a start image, judged as silent video. MiniMax H3 ranks #7 of 34.
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.13 | per second |
| Additional | $0.052 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
| $0.13 | |
| $0.025 | |
| $0.05 | |
| $0.126 | |
| $0.126 |
Give your agent the model details, code and documentation.
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "minimax/h3",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "minimax/h3",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "minimax/h3",
"prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
MiniMax H3 takes image, text as input and returns video.
MiniMax H3 became available on July 31, 2026.
MiniMax H3 costs $0.13 per second on AI/ML API, billed as you go with no subscription.
MiniMax H3 costs $0.13 per second on AI/ML API, billed as you go with no subscription.
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.