All models

MiniMax Hailuo 2.3

minimax/hailuo-2.3
MiniMax Video GenerationCinematicImage-to-Video

A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across text-to-video and image-to-video workflows.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "minimax/hailuo-2.3",
    "prompt": "<your prompt>"
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "minimax/hailuo-2.3", "prompt": "<your prompt>"}'

Examples

Parameters

Input
duration number optional default: 6

Length of the output in seconds.

fast_pretreatment boolean optional default: false

Faster input pre-processing (may trade a little quality for speed).

first_frame_image string optional

Image to use as the first frame of the video.

prompt string optional

Text prompt describing what to generate.

prompt_optimizer boolean optional default: true

Let the model automatically optimize your prompt.

resolution string optional default: "768P"

Output resolution / quality tier.

Output
status: string
task_id: string
video: string