Skip to main content
MiniMaxNov 10, 2026New

MiniMax H3 Image

minimax-h3-imageAnonymized

MiniMax H3 Image is MiniMax’s image model for text-to-image generation, rendering at 1K, 2K and 4K in aspect ratios from 21:9 to 9:21. It pairs with MiniMax H3 Image Edit for changing and combining images.

from$0.04
per image
4K
max resolution, 3 sizes
11
aspect ratios, 1:1 default

Same prompt, other models

Every image model renders the same reference prompts, so their results line up side by side.

Photorealistic close-up portrait of a weathered fisherman at golden hour, 85mm lens, shallow depth of field, natural skin texture

Pricing

Billed per image in USD, by resolution. Each resolution is drawn to scale.

1K · default2K4K
Per image$0.04$0.04$0.10
Edit$0.06
Extra input image$0.0194
2x upscale$0.02
4x upscale$0.08

Estimate a batch

Resolution
$0.04per image
$40.00for 1,000 images

Against other image models

How it comparesamong 51 image models
Price per imagecheaper than 64%$0.04
Prompt limitlonger than 42%10,000 characters

Further right is better. Hover a dot for its model.

Capabilities

What the family does, and every shape it renders.

Generateminimax-h3-image
Editminimax-h3-image-edit · up to 16 images
Upscale2x $0.02 · 4x $0.08
Repeatableseed

Aspect ratios

1:15:44:33:216:921:94:53:42:39:169:21

Specs

Model ID
minimax-h3-image
Edit model ID
minimax-h3-image-edit
Endpoint
POST /api/v1/image/generate
Resolutions
1K, 2K, 4K · default 1K
Aspect ratios
11 · default 1:1
Prompt limit
10,000 characters
Steps
default 20, max 50
Privacy
Anonymized
Weights
Closed
Added
Nov 10, 2026

Quickstart

Generate with Venice’s image endpoint, or with the OpenAI-compatible one from any OpenAI SDK.

curl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-image",
"prompt": "A retro travel poster with the bold headline \"VENICE\" in large condensed serif type, sunset color palette",
"resolution": "1K",
"aspect_ratio": "1:1"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelminimax-h3-imageRequired
promptUp to 10,000 charactersRequired
resolution1K | 2K | 4KDefault 1K
aspect_ratio11 ratiosDefault 1:1
stepsUp to 50Default 20
seedIntegerRepeats a result
variants1 – 4Images per request
formatwebp | png | jpegDefault webp
safe_modetrue | falseDefault true, which blurs adult content