MiniMax H3 X API: 1080p Video

Name: MiniMax H3 X API
SKU: minimax/h3-x/text-to-video
Price: 0.11 USD
Availability: InStock

About MiniMax H3 X

MiniMax H3 X creates 2–15-second videos with sound from text, an opening image or reference material. Choose 480p, 720p or 1080p, with 720p as the default. Image-to-video also accepts an optional closing frame.

Call it with the model name minimax/h3-x/text-to-video on POST /jobs/createTask, from $0.11.

Introduction

MiniMax H3 X Text to video turns a prompt into a 2 to 15 second clip at 480p, 720p or 1080p.

Choose a mode by starting material

What you have	Mode
only an idea	MiniMax H3 X Text to video
a frame to animate, with an optional closing frame	MiniMax H3 X Image to video
people, outfits, places, motion clips or voices	MiniMax H3 X Reference to video

Key features

Spoken lines

A line in double quotes was spoken word for word in our speech-to-text checks, with matching lip movement.

Timed shots

List shots with start times and the clip cuts where you asked. In a 15-second test the cuts landed at about 5 and 10 seconds.

Six aspect ratios

16:9, 9:16, 1:1, 4:3, 3:4 and 21:9.

Sound with every clip

Stereo sound, effects and music follow the prompt.

Request parameters

Parameter	Required	Description
`prompt`	Yes	Describe what you want to make.
`resolution`	No	Choose an available output size. 480p · 720p · 1080p · Default: 720p
`aspect_ratio`	No	The shape of the frame: wide, square or tall. 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9 · Default: 16:9
`duration_seconds`	No	Length of the generated clip. ≥ 2 · ≤ 15 · Default: 5
`enable_prompt_expansion`	No	Lets the model add detail to a short prompt. Default: false

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.

Option	USD per second
resolution 480p	$0.022
resolution 720p	$0.032
resolution 1080p	$0.045

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

Dialogue scenes

A short exchange between two characters, lines in quotes.

Multi-shot sequences

A wide shot, a close-up and a medium shot in one clip.

Vertical clips

9:16 for phones.

Prompt guide & pro tips

Quote the dialogue

Put spoken lines in double quotes and say who speaks.

Give the shots times

"From 0 to 4 seconds... At 4 seconds the shot cuts to...". Repeat who is in the scene.

Choose the input mode

Start with text to video when you have no reference material. Use image to video to animate a starting image, or reference to video to guide a clip with images, video or audio references.

Keep prompt expansion off

It made no visible difference in our tests, so keep it off for literal direction.

API quick start

Call the MiniMax H3 X API in three steps

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.
Send the request. POST /jobs/createTask with model minimax/h3-x/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
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-x/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "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 X API questions

How much does the MiniMax H3 X API cost?

MiniMax H3 X starts at $0.11 for a 5-second clip with Create Video, its cheapest task. Prices by option: 480p $0.022 per second, 720p $0.032 per second, 1080p $0.045 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 X in the API?

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

About MiniMax H3 X: Does it make sound, and can it speak lines?

H3 X creates AAC stereo audio with its H.264 MP4 picture; write dialogue inside double quotes and describe the surrounding sound separately.

About MiniMax H3 X: How many references can I use?

An H3 X reference scene accepts 9 images, 2 videos totalling 15 seconds and 3 audio clips at most; name their roles with Image 1, Video 1 and Audio 1.

How does MiniMax H3 X compare with MiniMax H3?

H3 X and H3 X Turbo accept the same parameters, but no controlled comparison here establishes that X produces better pictures; Turbo has the shorter measured wait.

What is the difference between MiniMax H3 X and MiniMax H3 X Turbo?