by MiniMax

MiniMax's H3 image model: 1K to 4K stills and edits guided by up to 16 pictures

minimax/h3-image/text-to-image
  • Up to 4K
  • Up to 16 reference images
  • 15 aspect ratios
  • Create Image
  • Edit Image

About MiniMax H3-Image

MiniMax H3-Image is MiniMax's image model, released in November 2026. This is MiniMax's hosted version: it makes pictures at 1K, 2K or 4K and edits with one to sixteen source pictures, which you name in the prompt as image 1, image 2 and so on.

Call it with the model name minimax/h3-image/text-to-image on POST /jobs/createTask, from $0.036.

Introduction

MiniMax H3-Image turns a written scene into a still through MiniMax's hosted version, with no seed control.

Key features

Three resolution settings cover approximately 1, 4 and 16 megapixels. Our perfume sample showed clear NOIR 07 lettering on its bottle.

Request parameters

ParameterRequiredDescription
promptYesDescribe what you want to make.
resolutionNoChoose an available output size. 1k · 2k · 4k · Default: 1k
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 2:1 · 1:2 · 3:1 · 1:3 · 5:4 · 4:5 · Default: 1:1
output_formatNoFile type of the result. jpeg · png · webp · Default: png

Pricing

Prices are in USD and charged to your PopNow 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.

OptionUSD per image
resolution 1K$0.036
resolution 2K$0.036
resolution 4K$0.108

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

Use written prompts for product photographs, club scenes or clothed editorial portraits, with short labels where needed.

Prompt guide & pro tips

Write connected English sentences describing the subject, setting and lighting. Quote short label text, then choose aspect_ratio and resolution separately.

API quick start

Call the MiniMax H3-Image 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 are billed in USD from your PopNow balance.
  2. Send the request. POST /jobs/createTask with model minimax/h3-image/text-to-image 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-image/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "output_format": "png"
  }
}'

# 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-Image API questions

How much does the MiniMax H3-Image API cost?

MiniMax H3-Image starts at $0.036 per image with Create Image, its lowest-priced task. Prices by option: 1K $0.036 per image, 2K $0.036 per image, 4K $0.108 per image. API usage is charged in USD to your PopNow 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-Image in the API?

Put minimax/h3-image/text-to-image for Create Image; minimax/h3-image/edit for Edit Image in the model field of POST /jobs/createTask.

How do the hosted and open-weight choices differ?

This MiniMax-hosted option has three size tiers, up to sixteen editing inputs and no seed field. [Open Weights](/models/minimax-h3-image-open) offers five tiers and a seed; [Open Weights LoRA](/models/minimax-h3-image-open-lora) adds LoRA files.

What should I call my references in the prompt?

Use image 1 for the first upload and image 2 for the second, continuing in that order. Omit aspect_ratio on an edit to let the model choose a shape from the inputs and instruction.

Can it write words on a product?

Our bottle sample rendered NOIR 07 clearly, and the club sample contained a readable MIDNIGHT JAZZ sign. Those observations support short labels and signs, without a promise for long text.

How long did the hosted model take in testing?

In our tests the model took about 12–15 seconds at 1k and about 20 seconds at 4k; queueing and file transfer are additional.

What are the limits of the MiniMax H3-Image API?

Resolutions: 1K · 2K · 4K; Aspect ratios: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +9; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try MiniMax H3-Image without writing code?

Run MiniMax H3-Image 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-Image Open Weights runs MiniMax's open checkpoint on a different host, with five sizes, a seed and up to nine pictures per edit, and costs less at 1K. Pick the hosted version for edits that need more than nine pictures.

More about MiniMax H3-Image