Hailuo 2.3

How to use Hailuo 2.3

1. Fill in Prompt in the form on this page, and pick the task to run.
2. Adjust anything in the parameter table below — the defaults are the platform's recommended values.
3. Run it; signing in starts the charge, and the result (Image to video) appears above the form, ready to download.

Use it from the API

The same run, as a request. Send your API key as a bearer token; poll the returned request_uid until it is done.

curl -X POST https://api.melunox.com/v1/ai/async/tasks \
  -H "Authorization: Bearer $WISAVEN_API_KEY" \
  -H "X-App-Id: wisaven" -H "Content-Type: application/json" \
  -d '{
  "model": "hailuo-2-3",
  "task": "image-to-video",
  "input": {
    "prompt": "your prompt here",
    "resolution": "768P",
    "duration": "6"
  }
}'

At a glance

Developer

MiniMax

Can do

Image to video, Text to video

Credits per run

—

Typical time

~120s

Added

2026-08-11

Parameters

What the model takes. The form above is generated from exactly this list, and the API accepts the same field names.

What Hailuo 2.3 costs

Hailuo 2.3 costs usage-based pricing, charged at the platform's live rate, usually back in around 120 seconds. Credits are shared across every workspace, new accounts start with free ones, and a failed run is refunded.

Hailuo 2.3 compared with other Video models

Same workspace, different trade-offs — credits, speed and what each one can be asked for.

Questions