hailuo-2-3 API
Generate cinematic AI videos with the Hailuo 2.3 API via API in One. Image-to-video generation with standard and pro modes. 30–85 credits per video.
Use this in the request body model field.
The currently implemented BFF route.
Input types: image
Keys are managed by the shared dashboard.
Use callback_url on supported async tasks.
Service highlights
Marketplace-style signals backed by the current live route, without copying external SLA, discount, login, or payment claims.
This page only shows endpoints implemented under /api/v1. /api/v1/videos/generations
Use callback_url when supported, or poll the task status route for results.
Top-up, orders, credit balance, and profile continue through the existing shared console.
Your browser only holds an API in One key; provider calls stay server-side.
Call contract
Use these fields to integrate the current live model route.
- Base URL
https://apiin.oneClients call same-origin APIs; the server BFF forwards to the Worker.- Authorization
Authorization: Bearer <API_KEY>Managed by the existing Dashboard API Keys page.- Model field
hailuo-2-3Send this value in the request body model field.- Result path
/api/v1/tasks/{task_id}Async jobs return task_id, then use status polling.- Billing path
/billing/creditsUses the existing credits, orders, and top-up logic.
Runtime behavior
This model creates an async task, returns a task_id, then resolves through the real status route.
API Console
Switch between real models on this endpoint, choose a live route, and generate request examples from the current catalog payload.
curl --request POST \
--url https://apiin.one/api/v1/videos/generations \
--header 'Authorization: Bearer <API_KEY>'
--header 'Content-Type: application/json' \
--data-raw '{
"model": "hailuo-2-3",
"prompt": "A golden retriever running through a sunflower field at sunset, slow motion",
"image": "https://example.com/golden-retriever.jpg",
"duration": "6",
"resolution": "768P"
}'/api/v1/tasks/{task_id}Endpoint decision panel
Evaluate cost, provider coverage, and production integration behavior across live models on this implemented endpoint.
Sorted by base credits from low to high.
Use callback_url when supported, or poll the task status route for results.
Live capabilities
These capabilities come from the current model config and backend route. Unreleased APIs are not listed.
Use the same API in One key as the rest of the routed catalog
Use the same API in One key as the rest of the routed catalog
Cinematic motion quality rivaling top
Cinematic motion quality rivaling top-tier models
Unified billing with all other live models
Unified billing with all other live models
Webhook support for async completion
Webhook support for async completion
Request format
Clients call same-origin API routes; the server BFF forwards to the matching Worker.
POST/api/v1/videos/generations30 creditsHigh-quality AI video generation by MiniMax. Supports image-to-video with standard and pro quality modes, cinematic motion quality.
Parameters
promptstringText description of the video to generate
RequiredimagestringReference image URL for image-to-video generation
RequiredmodelstringSub-model: "hailuo/2-3-image-to-video-standard" (30–45cr) or "hailuo/2-3-image-to-video-pro" (45–85cr)
Optional · Default hailuo/2-3-image-to-video-standarddurationstringVideo duration: "6" or "10" seconds
Optional · Default 6resolutionstringOutput resolution: "768P" or "1080P"
Optional · Default 768PExample request
curl -X POST https://apiin.one/api/v1/videos/generations \
-H "Authorization: Bearer aio_your_api_key" \
-H "Content-Type: application/json" \
--data-raw '{
"model": "hailuo-2-3",
"prompt": "A golden retriever running through a sunflower field at sunset, slow motion",
"image": "https://example.com/golden-retriever.jpg",
"duration": "6",
"resolution": "768P"
}'Models on the same endpoint
These live models use the same implemented BFF endpoint and can be switched by changing the model field.
grok-videovideo · 24 credits/api/v1/videos/generations🎞️ltx-2video · 24 credits/api/v1/videos/generations/api/v1/videos/generations
wan-2-6video · 80 credits/api/v1/videos/generations/api/v1/videos/generations
kling-3video · 300 credits/api/v1/videos/generationsEndpoint model comparison
Compare real models behind this implemented route by cost, provider, runtime mode, input, output, and backend node.
node51
grok-videoxAIAsync tasktext + image -> video24 credits$0.24node31🎞️ltx-2LightTricks / WaveSpeedAsync tasktext + image + video + audio -> video24 credits$0.24node50node38
wan-2-6AlibabaAsync tasktext + image + video -> video80 credits$0.80node35node65
kling-3KuaishouAsync tasktext + image -> video300 credits$3.00node75node66Integration flow
These steps use the current live route and shared account system; login, payment, orders, credits, and profile remain shared.
Create a shared API key
Create a key in the existing dashboard. Top-up, orders, credit balance, and profile stay in the shared console.
Call the real endpoint
Send a request with the endpoint, model id, and parameters shown on this page. /api/v1/videos/generations
Poll task status
Async media and tool jobs use /api/v1/tasks/{task_id}; chat models return a direct response.
Task status route
After creating image, video, audio, or tool tasks, poll the real task endpoint for results.
GET/api/v1/tasks/{task_id}Check generation task status and result.Pricing
30–85 credits per video (~$0.30–$0.85)
Use cases
These workflows are supported by the current model and backend node.
Create short-form video content for social media marketing
Animate product photos into dynamic marketing videos
Build AI video generation into your creative workflow tools
Animate still images into dynamic video clips
FAQ
How much does the Hailuo API cost?
Standard mode: 30 credits (6s 768P), 45 credits (10s or 1080P). Pro mode: 45–85 credits depending on duration and resolution.
What video lengths does Hailuo 2.3 support?
Hailuo 2.3 generates 6 or 10 second video clips at 768P or 1080P resolution.
What is the difference between standard and pro?
Pro mode produces higher quality videos with better motion fidelity. Standard mode is cheaper and still produces excellent results.