MiniMax H3 Image API
MiniMax H3 Image is MiniMax's image generation and editing model, released on November 11, 2026. On APIMart you call it with the model ID minimax-h3-image for text to image and reference-image editing at 1K, 2K or 4K.
Service Highlights
- Official Discounts
- Pay-as-you-go
- Fast & Low Latency
Image link valid for 72 hours
MiniMax H3 Image API Pricing
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
minimax-h3-imagePrices are estimates; actual cost is billed by token usage. | 1K/2K | 0.1891Credits/pic~$0.0189/pic | 0.1797Credits/pic~$0.018/pic | 0.1702Credits/pic~$0.017/pic | 0.2364Credits/pic~$0.0236/pic | 20% |
| 4K | 0.628Credits/pic~$0.0628/pic | 0.5966Credits/pic~$0.0597/pic | 0.5652Credits/pic~$0.0565/pic | 0.785Credits/pic~$0.0785/pic | 20% |
* Actual costs are subject to final output.
* Billed by tokens. The rows are single-image text-to-image estimates: image output plus about 2,000 text input tokens for prompt enhancement. Reference images add image input tokens. The cost field of each task shows the actual charge.
MiniMax H3 Image API: Text to Image and Image Editing up to 4K
Generate images from a prompt, or edit with up to 16 reference images. Choose 1K, 2K or 4K with any aspect ratio from 1:3 to 3:1, or set exact pixels up to 20 million. One request returns up to 10 images, and built-in prompt enhancement expands short prompts for you.
MiniMax H3 Image API Example: Text to Image and Image Editing
Call MiniMax H3 Image on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the image URLs.
- 1
Authenticate MiniMax H3 Image API requests
Save your APIMart key in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
- 2
Submit a MiniMax H3 Image task
POST /v1/images/generations with model minimax-h3-image, your prompt, size and resolution. Add image_urls to edit with reference images. The task ID is in data[0].task_id.
- 3
Get the generated images
Poll GET /v1/tasks/{task_id} every 3 to 5 seconds until status is completed, then read the image URLs from data.result.images[0].url. Results are kept for 72 hours, so download them in time.
See the MiniMax H3 Image API reference for every parameter, size rule and response field.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-image",
"prompt": "A cozy coffee shop by the sea at sunset, photorealistic, warm tones",
"size": "16:9",
"resolution": "2K"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "minimax-h3-image",
"prompt": "A cozy coffee shop by the sea at sunset, photorealistic, warm tones",
"size": "16:9",
"resolution": "2K"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-image",
"prompt": "Put the jacket from the second image on the person in the first image, keep the background unchanged",
"image_urls": [
"https://example.com/person.jpg",
"https://example.com/jacket.png"
],
"resolution": "2K"
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"MiniMax H3 Image API Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: minimax-h3-image | Use minimax-h3-image. |
prompt | string | Required | Default: — | Image description, 1 to 32,000 characters after trimming. |
size | string | Optional | Default: auto | auto, an aspect ratio such as 16:9 (1:3 to 3:1), or pixels such as 2048x1152 (655,360 to 20,000,000 pixels in total). |
aspect_ratio | string | Optional | Default: — | Another way to pass the aspect ratio, such as 16:9. If set, it overrides size. |
resolution | string | Optional | Default: 4K | 1K, 2K or 4K. Cannot be used when size is in pixels. |
n | integer | Optional | Default: 1 | Number of images, 1 to 10. |
image_urls | string[] | Optional | Default: — | Up to 16 reference images as URLs or Base64 data URIs. Adding them switches to editing. |
prompt_optimizer | boolean | Optional | Default: true | Expands the prompt before generating. false works only for text to image with an explicit size. |
output_format | string | Optional | Default: jpeg | jpeg, png or webp. |
output_compression | integer | Optional | Default: 95 | Compression quality from 0 to 100. Ignored for png. |
watermark | boolean | Optional | Default: false | Adds a visible AI-generated watermark to the image. |
