HiAPI
OverviewModel MarketplaceAPI KeysUsage StatisticsCall LogsBillingReferralPlaygroundStorageChangelogContact UsSettings
Display unit
N
Powered by hiapi
Settings

Welcome

Contact Us

MiniMax H3 combines native 2K text-to-video, first and last frame control, and multimodal reference video under one model ID. Compare the workflows, check live pricing, and validate a result in Playground before integrating it.

Provider: MiniMax

Category: video generation

Endpoint: /v1/tasks

Status: Available

Cost: See live page pricing

Back to Models

MiniMax H3 Video Generator

New
by MiniMaxVideo

MiniMax H3 is a native 2K multimodal video model for text-to-video, first/last-frame control, and reference-driven generation with images, video, and audio across 4 to 15 seconds.

Pricing

Standard Usage

237 Credits/ s

Input

Frames

Use images to control the first and last frame.

Optional

Upload the first-frame image that controls how the video begins

Upload the last-frame image that controls how the video ends

0 / 7000
5s
4s1-second steps15s

Choose 4-15 seconds in 1-second steps

More parameters

Upload assets

Preview after upload
0/3

Upload reference audio files up to the model limit

0/3

Upload reference videos up to the model limit

Generation preferences

Whether to add an AI-generated watermark

Estimated cost1,189 Credits237 Credits / s × 5s

Output

Ready for generation

Configure your parameters and click "Run" to see the output here.

--

CAPABILITY & ADOPTION

One model for three native 2K video workflows

MiniMax H3 combines native 2K text-to-video, first and last frame control, and multimodal reference video under one model ID. Compare the workflows, check live pricing, and validate a result in Playground before integrating it.

Evaluate capability and live price

All three workflows share one model ID. Pricing comes from the current HiAPI billing configuration rather than a hard-coded content claim.

View live MiniMax H3 usage pricing

Use one source for the request contract

The API reference owns parameters, field combinations, media limits, callbacks, and copyable request examples.

Read the MiniMax H3 API parameter and schema reference

Move from first task to production

The tutorial focuses on workflow choice, task states, error diagnosis, idempotency, and output storage without duplicating the schema.

Follow the MiniMax H3 integration and debugging tutorial
Need to compare models and billing tiers?View live pricing for all models

Frequently asked questions

What type of video model is MiniMax H3?

It is prompt-led and can also use endpoint frames or image, video, and audio references according to the active contract.

Which output settings does MiniMax H3 support?

4-15 seconds, 2K, and 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive.

Can it generate sound or use audio references?

Optional image, video, and audio references; generated audio

How is MiniMax H3 billed?

Billing follows output duration and the live tier. Resolution, mode, or audio differences are reflected by the page price and task record.

How do I call the MiniMax H3 API?

POST an asynchronous task to /v1/tasks with model set to minimax-h3 and place parameters inside input.