Black Friday Sale 2026. Get up to 20% bonus credits.

Ends inSee the offer

MiniMax-H3-Image-Highspeed

Input price
$2.30/1M tokens
Output price
—
Modalities
Text · Image → Text · Image

Pricing

Per million tokens

API call price

Input

$2.30

Output

—

Cache write

—

Cache read

—


Integration & capabilities

Supported protocols

Images API
Compatible formatOpenAI
Routes
POST /v1/images/generations
POST /v1/images/edits
POST /v1/images/variations
FeaturesStreaming
Request parametersmodel, prompt, n, size, quality

cURL Example

curl -X POST https://api.openmodel.ai/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "MiniMax-H3-Image-Highspeed",
    "prompt": "A cute cat",
    "n": 1,
    "size": "1024x1024"
  }'

Supported capabilities

Vision
Models can process image inputs and analyze them — a capability known as vision.
Image Input
Multimodal from the ground up, unlocking a wide range of image processing and computer vision tasks including image captioning, classification, and visual question answering.
Image Generation
Generate and edit images from text prompts.

Context & limits

Max images per prompt

16