MiniMax H3 Lite API

The same MiniMax H3 multimodal video model as minimax-h3, on a budget channel billed per second: 480P at $0.01/s and 768P at $0.02/s, any whole length from 1 to 15 seconds. One endpoint routes by what you send — a prompt alone is text-to-video, reference images lock character, product or style, reference audio drives voice and lip movement, or a first + last frame gives an interpolated shot. References are free. No reference video, no 2K.

Pricing (per second)

Resolution	Per second	5s	10s	15s
480P	$0.01	$0.05	$0.10	$0.15
768P (default)	$0.02	$0.10	$0.20	$0.30

Billed for the seconds you ask for, any whole number from 1 to 15. Reference images (up to 9) and reference audio (up to 3 clips) cost nothing extra. Charged only on success, refunded on failure.

Versus minimax-h3: same model, Lite is a fifth of the price at 768P ($0.02 vs $0.097/s) but has no native 2K, no reference video, 16:9 / 9:16 only. For 2K delivery or motion transfer from a reference video, use minimax-h3.

Authentication

All requests carry the API key in the header:

Authorization: Bearer YOUR_API_KEY

Generate a video

POST/api/v1/video/generations·GET/api/v1/video/generations?task_id=

# Text-to-video (prompt only). Add images / audio_list / first+last frame for the other modes.
curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3-lite",
    "prompt": "A girl with headphones nods to the beat in a bright studio, slow push-in, soft light",
    "duration": 5,
    "resolution": "768p",
    "ratio": "16:9"
  }'

# Reference images + reference audio (audio drives voice and lip movement; needs >= 1 image)
curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3-lite",
    "prompt": "The girl in Picture 1 sings along to Audio 1, gentle head movement, studio light",
    "images": ["https://example.com/ref1.png", "https://example.com/ref2.png"],
    "audio_list": ["https://example.com/voice.wav"],
    "duration": 10,
    "resolution": "768p"
  }'

# Poll until completed (result files are kept 7 days)
curl "https://api.apimodels.app/v1/video/generations?task_id=TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

Four modes, one endpoint

There is no mode switch — the request is routed by the fields you send:

Text-to-video — prompt only.
Reference images — prompt + images (1-9). Locks character, product or style; refer to them as Picture 1 / Picture 2 in the prompt.
Images + audio — prompt + images (>= 1) + audio_list (1-3 clips). Audio drives voice and lip movement; refer to it as Audio 1 in the prompt.
First + last frame — prompt + first_frame_url + last_frame_url (both required), without images / audio_list. A first frame on its own is treated as one reference image.

Parameters

Field	Required	Type	Description
model	Yes	string	minimax-h3-lite
prompt	Yes	string	Describe subject, action, camera motion, lighting and sound; up to 20,000 characters.
duration	No	number	Any whole second from 1 to 15, default 5. Billed for this many seconds.
resolution	No	string	480p ($0.01/s) or 768p ($0.02/s, default). No 1080p / 2k.
ratio	No	string	16:9 (landscape, default) or 9:16 (portrait). aspect_ratio is also accepted.
images	No	string[]	Reference images, up to 9 (public URL or base64). image_urls / reference_image_urls are also accepted. Free.
audio_list	No	string[]	Reference audio, up to 3 clips (mp3 / wav, URL or base64); needs at least one reference image. audio_urls / reference_audio_urls are also accepted. Free.
first_frame_url	No	string	First frame. With last_frame_url this is first/last-frame mode; on its own it counts as one reference image.
last_frame_url	No	string	Last frame. Must be sent together with first_frame_url.
callback_url	No	string	We POST the result to this URL on completion; omit it and poll the GET endpoint instead.

Notes

Async: create returns a taskId; poll GET /v1/video/generations?task_id= until completed, or pass callback_url. Measured turnaround: about 1.5 minutes for 480P·3s, 2.5 minutes for 768P·5s, 4.5 minutes for 768P·10s and 8 minutes for 768P·15s, plus queue time. Result files are deleted after 7 days — download or re-host promptly.
No reference video: a request carrying video_list / video_urls gets a clear 400 at create time — it is never dropped silently and billed anyway. Use minimax-h3 for motion transfer.
Parameter errors (duration outside 1-15, resolution or ratio outside the enums, more than 9 images / 3 audio clips, a last frame without a first, first/last frame mixed with references) return a synchronous 400 at create time — no task, no charge.
Field names are identical to minimax-h3, so switching between the two means changing model only.

Try it in the Playground

FAQ

How much does MiniMax H3 Lite cost?

Per second on apimodels.app: 480P $0.01/s and 768P $0.02/s, any whole length from 1 to 15 seconds — a 768P 10-second clip is $0.20. Reference images and audio are free. Only successful generations are charged; failures are refunded.

How do I call the MiniMax H3 Lite API?

POST /api/v1/video/generations with model minimax-h3-lite and a prompt. Optional: duration 1-15 (default 5), resolution 480p or 768p (default 768p), ratio 16:9 or 9:16, images (up to 9), audio_list (up to 3, needs an image), or first_frame_url + last_frame_url. Poll GET /api/v1/video/generations?task_id=xxx or pass callback_url. One API key covers every model on apimodels.app.

What is the difference between minimax-h3-lite and minimax-h3?

Same MiniMax H3 model. Lite is a fifth of the price at 768P ($0.02/s vs $0.097/s) but has no native 2K, no reference video, 16:9 / 9:16 only. Pick Lite for drafts, social clips and volume; pick minimax-h3 for 2K delivery or motion transfer from a reference video.