MiniMax H3 Image API — price per image and code examples

Checking statusPrice version 1 · in effect since Nov 14, 2026

Token rates

Text · Per 1M input tokensOfficial price $2.30$0.345
Image · Per 1M input tokensOfficial price $1.50$0.225
Image · Per 1M output tokensOfficial price $3.80$0.57
≈ Per image1 image 1K, short prompt$0.003174

  • Billed by the tokens each request uses; only images you receive count.
  • A failed or rejected request is not charged.
  • Results are kept for 24 hours, then deleted automatically.
85% off

About this model

MiniMax H3 Image creates a new image from a text prompt through POST /v1/images/generations, in the OpenAI Images format. A typical image costs about $0.003174; the bill follows the tokens of each request. It is paid from your USD balance; budget packs cover chat models only.

Images API reference →

Specification

Input and output
Text → image
Endpoint
/v1/images/generations
Response
b64_json + usage.cost
Stored results
24 hours
Smallest pack
Not in a pack

Processing time. A request can take 1–3 minutes. Set your client timeout to at least 630 seconds.

Cent AI adds no content filter of its own. The model's own moderation can refuse a prompt; a refused request is not charged. Acceptable use policy

Code

curl https://api.cent-ai.dev/v1/images/generations \
  -H "Authorization: Bearer $CENT_AI_KEY" \
  -H "Content-Type: application/json" \
  --max-time 630 \
  -d '{"model": "minimax-h3-image", "prompt": "A lighthouse at dawn, watercolor", "size": "1024x1024"}'

Set CENT_AI_KEY to a key from the dashboard. OpenAI SDKs use https://api.cent-ai.dev/v1. The request waits for the image, so keep the timeout long.

Questions

How much does MiniMax H3 Image cost on Cent AI?

About $0.003174 for a typical image. You pay for the input and output tokens of each request at the rates on this page, and only images you receive count. Before the model is called, the most the request can cost is held from your balance; the rest is released.

Why does a request take so long?

The model needs time to draw. After 15 seconds Cent AI sends the status line and a space every 15 seconds until the image arrives, so the connection stays open. Keep your client timeout at 630 seconds or more.

Am I charged when a request fails?

No. A request that fails or is refused releases the hold in full. If it fails after the status line was sent, the body carries an error object instead of data.

How do I pay?

Top up a prepaid USD balance with QRIS or USDT/USDC, or buy a budget pack once. Nothing renews automatically.

Try MiniMax H3 Image with one key

One prepaid balance for every model. Pay with QRIS or USDT/USDC.

Start free