API docs / Video models

Hailuo 2.3 API

Generate high-fidelity videos from text prompts or first frame images, optimized for realistic human motion, cinematic VFX, and expressive characters. Supports both text-to-video and image-to-video workflows with strong prompt and style adherence. Offers 768p and 1080p resolution options with 6 or 10-second duration (10 seconds only available at 768p). When using image input, the output video maintains the same aspect ratio as the source image, while text-only input defaults to 16:9 aspect ratio. Features a prompt optimizer to enhance input descriptions for better results.

Model id
minimax/hailuo-2.3
Provider
MiniMax
Output
Video
Price
From 98 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "minimax/hailuo-2.3". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/hailuo-2.3",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text prompt for generation

first_framearray of URLs

First frame image for video generation. The output video will have the same aspect ratio as this image.

Up to 1 files · Accepts image/*

resolutionstring

Default: 768p

One of: 768p, 1080p

duration_secondsnumber

Default: 6

One of: 6, 10

enhance_promptboolean

Use prompt optimizer

Default: true