MiniMax H3
MiniMax H3 turns text, images or references into video with sound. Call it through one API in three variants, Base, Character and Native, and upscale a finished video to twice its resolution.
Variants
Each variant has its own model ID and prices. Pick one, and the prices, playground and code below switch to it.
| Variant | About | From | View |
|---|---|---|---|
Base minimax-h3-base | $0.001941 / second | ||
Character minimax-h3-character | $0.001941 / second | ||
Native minimax-h3-native | $0.002911 / second | ||
Upscale minimax-h3-upscale | $0.001941 / second |
Compare outputs
Real, unedited outputs of each variant from the same prompt and settings.
Close-up of a young woman with freckles in a sunlit cafe. She looks up from her book, smiles warmly and says: "Hi, you made it!"
768p · fast · 5s · 16:9 · seed 20261027
MiniMax H3 Base
minimax-h3-base
MiniMax H3 for everyday video with sound, from text, images or references at 480p or 768p. Recommended for most prompts, and the cheapest.
Prices by route
| Route | Spec | Price |
|---|---|---|
Studio MiniMax H3 video with sound: Base, Character and Native at every tier, 480p and 768p. | Mode replace · Tier fast · Resolution 768p · Upscale none · Turbo false | $0.007762 / second |
| Mode replace · Tier fast · Resolution 768p · Upscale none · Turbo true | $0.01009 / second | |
| Mode replace · Tier standard · Resolution 768p · Upscale none · Turbo false | $0.009702 / second | |
| Mode replace · Tier standard · Resolution 768p · Upscale none · Turbo true | $0.012612 / second | |
| Mode replace · Tier enhanced · Resolution 768p · Upscale none · Turbo false | $0.015523 / second | |
| Mode replace · Tier enhanced · Resolution 768p · Upscale none · Turbo true | $0.02018 / second | |
| Mode replace · Tier quality · Resolution 768p · Upscale none · Turbo false | $0.019403 / second | |
| Mode replace · Tier quality · Resolution 768p · Upscale none · Turbo true | $0.025224 / second | |
| Mode ≠ replace · Tier fast · Resolution 480p · Upscale none · Turbo false | $0.001941 / second | |
| Mode ≠ replace · Tier fast · Resolution 480p · Upscale none · Turbo true · Reference videos | $0.002523 / second | |
| Mode t2v / i2v / r2v · Tier fast · Resolution 480p · Upscale 2x · Turbo false | $0.003881 / second | |
| Mode t2v / i2v / r2v · Tier fast · Resolution 480p · Upscale 2x · Turbo true · Reference videos | $0.004463 / second | |
| Mode ≠ replace · Tier standard · Resolution 480p · Upscale none · Turbo false | $0.002911 / second | |
| Mode ≠ replace · Tier standard · Resolution 480p · Upscale none · Turbo true · Reference videos | $0.003784 / second | |
| Mode t2v / i2v / r2v · Tier standard · Resolution 480p · Upscale 2x · Turbo false | $0.004851 / second | |
| Mode t2v / i2v / r2v · Tier standard · Resolution 480p · Upscale 2x · Turbo true · Reference videos | $0.005724 / second | |
| Mode ≠ replace · Tier enhanced · Resolution 480p · Upscale none · Turbo false | $0.005821 / second | |
| Mode ≠ replace · Tier enhanced · Resolution 480p · Upscale none · Turbo true · Reference videos | $0.007568 / second | |
| Mode ≠ replace · Tier quality · Resolution 480p · Upscale none · Turbo false | $0.007762 / second | |
| Mode ≠ replace · Tier quality · Resolution 480p · Upscale none · Turbo true | $0.01009 / second | |
| Mode t2v / i2v / first_last / r2v · Tier quality · Resolution 480p · Upscale 2x · Turbo false | $0.009702 / second | |
| Mode t2v / i2v / first_last / r2v · Tier quality · Resolution 480p · Upscale 2x · Turbo true | $0.01203 / second | |
| Mode ≠ replace · Tier fast · Resolution 768p · Upscale none · Turbo false | $0.003881 / second | |
| Mode ≠ replace · Tier fast · Resolution 768p · Upscale none · Turbo true · Reference videos | $0.005045 / second | |
| Mode t2v / i2v / r2v · Tier fast · Resolution 768p · Upscale 2x · Turbo false | $0.007762 / second | |
| Mode t2v / i2v / r2v · Tier fast · Resolution 768p · Upscale 2x · Turbo true · Reference videos | $0.008926 / second | |
| Mode ≠ replace · Tier standard · Resolution 768p · Upscale none · Turbo false | $0.005821 / second | |
| Mode ≠ replace · Tier standard · Resolution 768p · Upscale none · Turbo true · Reference videos | $0.007568 / second | |
| Mode t2v / i2v / r2v · Tier standard · Resolution 768p · Upscale 2x · Turbo false | $0.009702 / second | |
| Mode t2v / i2v / r2v · Tier standard · Resolution 768p · Upscale 2x · Turbo true · Reference videos | $0.011448 / second | |
| Mode ≠ replace · Tier enhanced · Resolution 768p · Upscale none · Turbo false | $0.011642 / second | |
| Mode ≠ replace · Tier enhanced · Resolution 768p · Upscale none · Turbo true · Reference videos | $0.015135 / second | |
| Mode ≠ replace · Tier quality · Resolution 768p · Upscale none · Turbo false | $0.015523 / second | |
| Mode ≠ replace · Tier quality · Resolution 768p · Upscale none · Turbo true | $0.02018 / second | |
| Mode t2v / i2v / first_last / r2v · Tier quality · Resolution 768p · Upscale 2x · Turbo false | $0.019403 / second | |
| Mode t2v / i2v / first_last / r2v · Tier quality · Resolution 768p · Upscale 2x · Turbo true | $0.02406 / second |
A task costs the price of the route that serves it. If a route fails, the task moves to the next route you allow and the charge changes to that route's price. Routes priced per token are charged an estimate up front and settled on the tokens actually used. Failed tasks are refunded in full.
Price calculator
| Route | Estimate |
|---|---|
Studio | $0.019405 |
Estimates follow the same rules as billing. A route priced per token charges this estimate when the task is submitted and settles on the tokens the upstream reports when it finishes: the difference is refunded or charged. If your balance can't cover it, the balance goes negative until your next top-up.
Input
PNG, JPEG or WebP, up to 10 MB each. Uploads are kept for 72 hours.
An MP4 link, up to 100 MB.
MP3 or WAV links, up to 100 MB each.
Fill in the required fields to see the price.
Request body
{
"model": "minimax-h3-base",
"input": {
"tier": "fast",
"duration": 5,
"resolution": "768p",
"aspect_ratio": "16:9",
"upscale": "none",
"turbo": false
}
}Output
Run the model to see the result here.
| Field | Description | Allowed values | Default |
|---|---|---|---|
| prompt | What happens in the video. Required, except in replace mode, where it is an optional extra instruction (up to 2,000 characters). | — | — |
| mode | t2v (text only), i2v (first frame), first_last (first and last frame), last_frame (last frame only), r2v (reference images, videos or audio), replace (the person in one image acts out one motion video) or upscale (an earlier task's video at twice the resolution). Inferred from the inputs when omitted; last_frame and replace must be asked for. | t2v, i2v, first_last, last_frame, r2v, replace | — |
| image_urls | Images: the frame for i2v and last_frame, two for first_last, references for r2v, the person for replace. | — | — |
| video_urls | Reference videos for r2v, or the motion clip for replace: MP4, as http(s) links or base64 data URLs. | — | — |
| audio_urls | Reference audio for r2v: MP3 or WAV, as http(s) links or base64 data URLs. | — | — |
| motion_start | replace: where in the motion clip the motion starts, in seconds. The clip must run on for the whole duration. | — | — |
| tier | Render tier: fast, standard, enhanced or quality. Higher tiers look better and cost more per second. | fast, standard, enhanced, quality | fast |
| duration | Length in seconds. Most models price per second. | 4–15 | 5 |
| resolution | 480p, 720p, 768p, 1080p or 4k. | 480p, 768p | 768p |
| aspect_ratio | e.g. 16:9, 9:16, 1:1, adaptive. | 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 | 16:9 |
| upscale | none or 2x: upscale the output to twice the resolution, at a surcharge per second. Not every tier, model or mode offers it. | none, 2x | none |
| turbo | Render faster for 30% more on the generation. Best effort: without room it runs at the normal speed, and the difference is refunded when the task completes. | false, true | false |
| enhance_prompt | Let the model rewrite the prompt before generating. Replace mode always does. | — | — |
| keep_video_audio | Use the reference video's own sound instead of generating it. Needs a reference video. | — | — |
| seed | A fixed seed, for repeatable results. | — | — |
Submit a task, then poll it until it finishes, or pass callback_url to have the result posted to you.
curl https://api.janvia.io/v1/tasks \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-base",
"input": {
"prompt": "A drone shot over a misty forest at sunrise",
"duration": 5,
"resolution": "768p",
"aspect_ratio": "16:9"
}
}'
# Then poll until "status" is "completed" or "failed":
curl https://api.janvia.io/v1/tasks/TASK_ID -H "Authorization: Bearer $API_KEY"