Hailuo hailuo-2.3-image-to-video-standard API
A model variant exposed through RunAPI's unified AI API.
Operational
·
video
·
Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/hailuo -g
Or paste this prompt to your AI agent:
Install the Hailuo skill for me: 1. Clone https://github.com/runapi-ai/hailuo 2. Copy the skills/hailuo/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Switch variant
RESUMEN
Hailuo hailuo-2.3-image-to-video-standard is available through the same RunAPI auth, SDKs, and agent skill workflow.
- Unified endpoint
- SDK snippets
- Agent install path
- Las generaciones fallidas no se cobran
PRECIOS
PRECIOS
Las generaciones fallidas no se cobran
Image to video
$0.30-$0.50
/ video
Duration seconds: 6 · Output resolution: 768p
$0.30
Duration seconds: 6 · Output resolution: 1080p
$0.50
Duration seconds: 10 · Output resolution: 768p
$0.50
FICHA TÉCNICA
FICHA TÉCNICA
| Model ID | hailuo-2.3-image-to-video-standard |
| Proveedor | MiniMax |
| Modalidad | video |
| Task type | asynchronous |
| Facturación | call |
| Endpoint | /api/v1/hailuo/image_to_video |
| Commercial | Yes |
| Status | Operational |
INICIO RÁPIDO
Quickstart — hailuo-2.3-image-to-video-standard
curl -X POST https://runapi.ai/api/v1/hailuo/image_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hailuo-2.3-image-to-video-standard",
"image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
"prompt": "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
}'
import { HailuoClient } from "@runapi.ai/hailuo";
const client = new HailuoClient();
const result = await client.imageToVideo.run({
model: "hailuo-2.3-image-to-video-standard",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge.",
});
require "runapi/hailuo"
client = RunApi::Hailuo::Client.new
result = client.image_to_video.run(
model: "hailuo-2.3-image-to-video-standard",
image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 5-second clip of a glass marble rolling across a wooden desk and falling off the edge."
)
CÓMO FUNCIONA
How to use hailuo-2.3-image-to-video-standard
01
Choose endpoint
Pick the endpoint and copy the SDK snippet.
02
Pass model ID
Use this variant ID in the request body.
03
Run task
Submit the request and store the returned task ID.
04
Collect output
Poll or receive the callback when the task finishes.
DIFERENCIAS
How hailuo-2.3-image-to-video-standard compares
VS HAILUO-02-IMAGE-TO-VIDEO-PRO
Same 2.3 motion improvements at lower resolution and cost
1080p image-anchored video; image sets first frame
VS HAILUO-02-IMAGE-TO-VIDEO-STANDARD
Same 2.3 motion improvements at lower resolution and cost
768p image-anchored video; budget tier
VS HAILUO-02-TEXT-TO-VIDEO-PRO
Same 2.3 motion improvements at lower resolution and cost
1080p native text-to-video output
CASOS DE USO
Where to use this variant
Product video
Generate short production-ready clips from prompts.
Creative iteration
Test multiple directions quickly.
Agent workflows
Let agents create video assets via tool calls.
FAQ
Frequently asked questions about hailuo-2.3-image-to-video-standard
How do I select hailuo-2.3-image-to-video-standard?
Pass the model ID shown in the quickstart.
Is pricing usage-based?
Yes. Pricing is metered per call or unit.
Other Hailuo variants
hailuo-02-image-to-video-standard
Cheapest
02-image-to-video-standard
$0.300 / call
hailuo-02-text-to-video-standard
02-text-to-video-standard
$0.500 / call
hailuo-02-image-to-video-pro
Quality
02-image-to-video-pro
$0.570 / call
hailuo-02-text-to-video-pro
Quality
02-text-to-video-pro
$0.570 / call
hailuo-2.3-image-to-video-pro
Quality
2.3-image-to-video-pro
$0.900 / call
Related models
Text, image, and edit-video generation with 720p and 1080p output, duration control, first-frame image support, ordered reference images for character-guided clips, and source-video editing.
InfiniteTalk
Audio-driven talking-head animation — lip-sync and animate a portrait from any audio input.
Video modification and transformation powered by Luma's Dream Machine model.
EMPEZAR