by MiniMax

Video with sound at 480p or 768p from text, images or references

minimax/h3-lite/text-to-video
  • Up to 768p
  • 4–15s clips
  • Start and end frames
  • Up to 9 reference images
  • 6 aspect ratios
  • Create Video
  • Image to Video
  • Reference to Video

About MiniMax H3 Lite

MiniMax H3 Lite creates 4–15-second videos with sound from text, a starting image or image, video and audio references. Choose 480p or 768p, with 768p as the default. Image-to-video also accepts an optional closing frame.

Call it with the model name minimax/h3-lite/text-to-video on POST /jobs/createTask, from $0.125.

Introduction

MiniMax H3 Lite Text to video turns a written prompt into a 4 to 15 second clip at 480p or 768p, with dialogue, effects and music generated in the same pass as the picture. A clip took about 22 to 25 seconds for a 4-second 480p clip in our runs.

Choose a mode by starting material

What you haveMode
only an ideaMiniMax H3 Lite Text to video
a frame to animate, with an optional closing frameMiniMax H3 Lite Image to video
people, outfits, places, motion clips or voicesMiniMax H3 Lite Reference to video

Key features

Sound and dialogue in one pass

Every MiniMax H3 Lite clip comes back with sound. Lines written in double quotes are spoken, and music or ambience follows the words you use for them, so a short scene needs no separate audio step.

Request parameters

ParameterRequiredDescription
promptYesDescribe what you want to make.
resolutionNoChoose an available output size. 480p · 768p · Default: 768p
aspect_ratioNoThe shape of the frame: wide, square or tall. 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9 · Default: 16:9
duration_secondsNoLength of the generated clip. ≥ 4 · ≤ 15 · Default: 5

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
resolution 480p$0.025
resolution 768p$0.04

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

Storyboards and pitch clips

Turn a written shot list into moving previews for a pitch or a script read. Each prompt on MiniMax H3 Lite returns a finished clip with sound, so the room hears the scene as well as seeing it, and a weak idea can be dropped before anything expensive is made.

Prompt drafts at volume

Writers and app builders can try many versions of a scene on MiniMax H3 Lite and keep the one that works, paying per second of output only. Changing one detail at a time, such as the camera, the outfit or the line of dialogue, shows quickly which version of the scene is worth a longer render.

Vertical clips with a line of dialogue

A 9:16 scene of 5 to 8 seconds with one quoted line and ambience fits social formats directly from MiniMax H3 Lite, with no editing pass for sound. Creators who post daily can keep a recurring setting and change only the action and the line in each new prompt.

Prompt guide & pro tips

Write the scene in order

On MiniMax H3 Lite, describe who is there, what they do first and next, where the camera is, and finish with an Audio: line for sound. A clear order gives cleaner motion than a list of adjectives, and naming the light, such as golden hour or neon, sets the mood quickly.

Keep dialogue short

On MiniMax H3 Lite, one or two quoted lines suit a 5 to 8 second clip; say who speaks each line so the right person moves their lips. Longer speeches get rushed or cut, so split them across several clips.

API quick start

Call the MiniMax H3 Lite API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
  2. Send the request. POST /jobs/createTask with model minimax/h3-lite/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "minimax/h3-lite/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "768p",
    "duration_seconds": 5
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

MiniMax H3 Lite price on other platforms

OptionsPopNowReplicate
480p$0.0250/ s$0.0125/ s
768p$0.0400/ s$0.0200/ s

Each platform's public API list price for the same model and settings, checked Nov 5, 2026.

MiniMax H3 Lite API questions

How much does the MiniMax H3 Lite API cost?

MiniMax H3 Lite starts at $0.125 for a 5-second clip with Create Video, its cheapest task. Prices by option: 480p $0.025 per second, 768p $0.04 per second. The API uses a separate USD balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for MiniMax H3 Lite in the API?

Put minimax/h3-lite/text-to-video for Create Video; minimax/h3-lite/image-to-video for Image to Video; minimax/h3-lite/reference-to-video for Reference to Video in the model field of POST /jobs/createTask.

MiniMax H3 Lite vs H3: which should I use?

Use H3 Lite to explore ideas and produce many variations at 480p or 768p. Use MiniMax H3 when you want the quality-focused tier, which also reaches 2K and longer clips. A common workflow is to draft on Lite and send only the keepers to H3.

Does H3 Lite support 1080p or 2K?

No. H3 Lite stops at 768p. A landscape 480p clip came back at 864 x 480. If you need 2K output, use MiniMax H3 instead.

Can H3 Lite do image to video?

Yes. Send one opening frame, optionally a closing frame, and describe the motion and sound that follow. There is no aspect-ratio field: the clip keeps the shape of your frame, which must be 256 to 5,760 pixels per side.

How fast is MiniMax H3 Lite?

A 4-second text-to-video clip finished in about 22 to 25 seconds at 480p in our runs; image to video and reference to video took about 33 seconds.

Does it generate sound, and can people speak?

Yes, every clip comes with sound made alongside the picture, so even a 480p draft has audio to judge. Write spoken words in double quotes and say who speaks them. On reference to video, up to 3 audio clips can set a voice or a sound, though the words themselves stay in the prompt.

What are the limits of the MiniMax H3 Lite API?

Clip length: 4–15 s; Resolutions: 480p · 768p; Aspect ratios: 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9; Prompt length (characters): 7,000. Requests outside these limits are rejected before anything is charged.

Can I try MiniMax H3 Lite without writing code?

Run MiniMax H3 Lite in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All MiniMax models

MiniMax H3 HighSpeed offers the same three input modes at 768p only. H3 Lite also offers 480p.

More about MiniMax H3 Lite