How is MiniMax H3 Lite different from MiniMax H3?

Lite is the lightweight variant that MiniMax positions as lower cost, for trying ideas and generating in bulk; H3 puts image quality first. Resolution: Lite outputs 480P or 768P, H3 outputs 768P or 2K. Inputs and length are the same (4–15 seconds; first frame, first + last frame, reference images / videos / audio), but Lite needs an explicit aspect ratio when you pass reference inputs. Their per-second rates differ; see each model’s pricing section.

Why do I get a 400 when I send reference images?

Most likely the ratio is missing or set to adaptive. With reference inputs Lite does not support adaptive, so pass one of 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9. This only applies to requests with reference images, videos or audio; with a first frame or first and last frames you can leave the ratio out.

How do I set resolution and length?

POST /v1/videos with model minimax/minimax-h3-lite, size "480P" or "768P", and seconds 4–15. A width×height size such as "854x480" also works and picks the tier by its short side. Leaving them out gives 768P, 5 seconds and 16:9.

MiniMax H3 Lite

Save 50%Official

minimax/minimax-h3-lite

MiniMax H3 Lite — the lightweight, lower-cost H3 variant: 4–15 sec at 480P or 768P, text-to-video, first/last frame, plus reference images, videos and audio.

Get an API key View code sample

Live model playground

Try MiniMax H3 Lite here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

asyncvideo

1Configure input

Prompt

0 / 20,000

First frame

Last frame

Reference images

Maximum estimated cost—

2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

Input modalities: TextImage
Output modalities: Video
Capabilities: Video generation · Text-to-video · Image-to-video · Reference voices · Reference images · Reference videos · First and last frame
Upstream release: 2026-10-26
RouteMux name: minimax/minimax-h3-lite
Official ID: MiniMax-H3-Lite

What is MiniMax H3 Lite

MiniMax H3 Lite is the lightweight, lower-cost variant of the MiniMax H3 family; MiniMax positions it for trying ideas and generating in bulk. It uses the same API as MiniMax H3 and outputs 480P or 768P, not 2K.

You start the same ways as with H3: from a prompt alone (text-to-video), from a first frame or a first and last frame (image-to-video), or from references: up to nine reference images, three reference videos and three reference audio clips (videos and audio each 2–15 seconds per clip, 15 seconds in total). Frame images and references cannot be mixed in one request, and a request takes at most 12 input files. Duration is any whole number of seconds from 4 to 15, and the aspect ratio can be 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9. Prompts can run to 7,000 characters.

One thing works differently from H3: with reference inputs (images, video or audio) you must pass an explicit ratio. Adaptive is not supported there, and leaving the ratio out returns a 400 before any job is created. With only a first frame, or first and last frames, the ratio follows the input image as usual.

Pricing is per output second, with one rate for 480P and another for 768P. Reference video adds a charge per input second at the rate of the chosen output tier; the first five reference images are free and each one after that is charged; reference audio is free. It uses the OpenAI Sora protocol and is asynchronous: the request returns a job, and you poll it for the finished video.

Before you choose

How is MiniMax H3 Lite different from MiniMax H3?: Lite is the lightweight variant that MiniMax positions as lower cost, for trying ideas and generating in bulk; H3 puts image quality first. Resolution: Lite outputs 480P or 768P, H3 outputs 768P or 2K. Inputs and length are the same (4–15 seconds; first frame, first + last frame, reference images / videos / audio), but Lite needs an explicit aspect ratio when you pass reference inputs. Their per-second rates differ; see each model’s pricing section.
Why do I get a 400 when I send reference images?: Most likely the ratio is missing or set to adaptive. With reference inputs Lite does not support adaptive, so pass one of 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9. This only applies to requests with reference images, videos or audio; with a first frame or first and last frames you can leave the ratio out.
How do I set resolution and length?: POST /v1/videos with model minimax/minimax-h3-lite, size "480P" or "768P", and seconds 4–15. A width×height size such as "854x480" also works and picks the tier by its short side. Leaving them out gives 768P, 5 seconds and 16:9.

MiniMax H3 Lite API pricing

OutputOfficial $0.025 /sec

$0.0125/secSave 50%

480P$0.0125 /secOfficial ~~$0.025~~
768P$0.02 /secOfficial ~~$0.04~~
Reference video · 480P$0.0125 /secOfficial ~~$0.025~~
Reference video · 768P$0.02 /secOfficial ~~$0.04~~
Reference images (first 5 free, then each)$0.01Official ~~$0.02~~

Key capabilities

480P or 768P: Two output resolutions, each with its own per-second rate.
4–15 seconds: Any whole-second length, not fixed presets.
Frames or references: First frame, first + last frame, or up to 9 reference images, 3 reference videos and 3 audio clips.
Asynchronous: Returns a job; poll it to get the video.
50% below official pricing: Billed per output second; both per-second rates are in the pricing section above.

Limited time10% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Interface and protocols

OpenAI Sora

Use any of these IDs to call this model via the API.

RouteMux nameminimax/minimax-h3-lite

Official IDMiniMax-H3-Lite

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

curl https://api.routemux.com/v1/videos \
  -H "Authorization: Bearer <ROUTEMUX_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-h3-lite",
    "prompt": "A quiet product shot of a glass observatory at dusk",
    "seconds": 5,
    "size": "1280x720"
  }'

base_url: https://api.routemux.com/v1

Performance (last 30 days)

2 requests · last 30 days

Total usage—

P50 first-token latencyInsufficient data (2 requests)

Avg throughputInsufficient data (2 requests)

Success rate—

Uptime · 24h

—

Success rate · 60d · from real requests

MiniMax H3 Lite FAQ

›What is MiniMax H3 Lite?

MiniMax H3 Lite — the lightweight, lower-cost H3 variant: 4–15 sec at 480P or 768P, text-to-video, first/last frame, plus reference images, videos and audio.

›How much does the MiniMax H3 Lite API cost?

Through RouteMux, MiniMax H3 Lite is billed per second, by resolution: 480P $0.0125, 768P $0.02. Each is below the official list price.

›How do I call MiniMax H3 Lite via API?

MiniMax H3 Lite is OpenAI-compatible: point your base URL at RouteMux and set the model field to minimax/minimax-h3-lite — no code changes needed.

›Which input and output modalities does MiniMax H3 Lite support?

MiniMax H3 Lite accepts text, image as input and produces video as output.

›When was MiniMax H3 Lite released?

MiniMax H3 Lite was released on October 26, 2026.

Sources

Reviewed by the RouteMux team on 2026-10-26

View as Markdown