All ModelsimageMiniMax H3 Image

MiniMax H3 Image

by MiniMax

Try on Kunya
image

MiniMax H3 Image

Open-weight-class 4K image model — strong prompt fidelity, text-to-image & editing with up to 16 refs

Model ID:minimax-h3-image

API Documentation

Generate images with this model.

POST/api/v1/images/generations
GET /api/v1/models?type=image
Request body
{
  "model": "minimax-h3-image",
  "prompt": "A serene mountain landscape at golden hour",
  "size": "1024x1024",
  "n": 1,
  "reference_image": "https://example.com/reference.jpg"
}
cURL example
curl -X POST https://kunya.ai/api/v1/images/generations \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"minimax-h3-image","prompt":"A serene mountain landscape at golden hour","size":"1024x1024","n":1,"reference_image":"https://example.com/reference.jpg"}'

Notes

  • •Returns a URL to the generated image in the response.
  • •Pass `reference_image` or `reference_images` for image-to-image editing.

Pricing

Cost$0.0286 per image

Capabilities

Streaming No
Vision No
Reasoning No
Tool Use No
ProviderMiniMax
Try on Kunya

Similar Models

Krea 2 Large

Krea

High-capacity Krea 2 generation — textured, flexible aesthetic, 1K, 1 reference

API Documentation

Qwen Image 3 Pro

Alibaba (Qwen)

Complex layouts, 10px text rendering, multilingual fonts — up to 6 images & 4 refs

API Documentation

SDXL Lightning

FAL AI (Stability AI)

Legacy ultra-fast SDXL — superseded by SD 3.5 Turbo

API Documentation

Recraft V4

FAL AI (Recraft)

Design-oriented image generation — brand assets, illustrations, and long text

API Documentation