Best-in-class human motion
It renders complex body movement and dance with greater fluidity and cleaner limb continuity, avoiding the phantom-limb and joint-snapping artifacts that affect many models on fast motion.
Generate cinematic AI video with MiniMax's Hailuo 2.3 through one unified API. A single REST endpoint, async jobs, and webhooks, with no separate MiniMax account to manage.
Integrate Hailuo 2.3 with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.
model: "hailuo-2.3" It renders complex body movement and dance with greater fluidity and cleaner limb continuity, avoiding the phantom-limb and joint-snapping artifacts that affect many models on fast motion.
It captures subtle facial performance, including small smiles, blinks, and emotional shifts, which suits close-up storytelling and character-driven scenes.
It handles lighting direction, shadow transitions, and color naturally, keeping scene geometry stable even under complex lighting and dynamic camera moves.
Beyond realism, it supports anime, illustration, ink-wash painting, game CG, and other distinct art styles with stable, vivid output.
It produces tracking shots and dynamic camera moves with consistent parallax, keeping subjects and backgrounds stable across the whole clip.
It keeps faces, brand objects, and on-screen logos sharp through motion, comes in standard and Fast variants, and holds the same low pricing as Hailuo 02.
A few outputs generated through the Hailuo 2.3 API on Apiframe.
A dancer performing a fast hip-hop routine, clean limb motion, studio lighting.
A close-up of an actor's face shifting from worry to a relieved smile, soft cinematic light.
A snowboarder carving down a powder slope, the camera tracking alongside, spraying snow.
An ink-wash style clip of a crane taking flight over a misty lake.
An image-to-video clip animating this portrait with subtle blinks and a gentle head turn.
A whiskey bar at night with warm pendant lighting, a slow camera push-in, moody reflections.
Send a single POST /v2/videos/generate request with your API key to
generate with Hailuo 2.3. The call returns a jobId you can poll or
receive via webhook.
curl -X POST https://api.apiframe.ai/v2/videos/generate \
-H "X-API-Key: afk_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "hailuo-2.3",
"hailuoParams": {
"image": "https://example.com/input.jpg",
"resolution": "768p",
"prompt_optimizer": true
}
}'import requests
response = requests.post(
"https://api.apiframe.ai/v2/videos/generate",
headers={
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
json={
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "hailuo-2.3",
"hailuoParams": {
"image": "https://example.com/input.jpg",
"resolution": "768p",
"prompt_optimizer": True
}
},
)
print(response.json()) # { "jobId": "...", "status": "QUEUED" }const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "hailuo-2.3",
"hailuoParams": {
"image": "https://example.com/input.jpg",
"resolution": "768p",
"prompt_optimizer": true
}
}),
});
const { jobId } = await response.json();
console.log(jobId);Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).
{
"jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
"status": "QUEUED"
}curl https://api.apiframe.ai/v2/jobs/JOB_ID \
-H "X-API-Key: afk_your_api_key_here"import requests, time
while True:
job = requests.get(
"https://api.apiframe.ai/v2/jobs/JOB_ID",
headers={"X-API-Key": "afk_your_api_key_here"},
).json()
if job["status"] in ("COMPLETED", "FAILED"):
break
time.sleep(2)
print(job["result"])let job;
do {
await new Promise((r) => setTimeout(r, 2000));
job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
headers: { "X-API-Key": "afk_your_api_key_here" },
}).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);Request parameters accepted by the Hailuo 2.3 endpoint. Model-specific options are nested under the params object shown below.
| Parameter | Type | Required | Default | Allowed / range | Description |
|---|---|---|---|---|---|
| prompt | string | required | — | — | Text description of what to generate. |
| model | string | required | "hailuo-2.3" | "hailuo-2.3" | The model identifier for this endpoint. |
| hailuoParams.image | string (URL) | optional | — | — | Use a still as the first frame. |
| hailuoParams.resolution | string | optional | "768p" | "768p", "1080p" | Resolution |
| hailuoParams.prompt_optimizer | boolean | optional | true | — | Let Hailuo rewrite your prompt for better results. |
Common questions about the Hailuo 2.3 API.
MiniMax's video generation model, released in October 2025 as the successor to Hailuo 02, supporting text-to-video and image-to-video.
Complex human motion and dance, expressive micro-expressions, physical realism, and stylized art like anime and ink-wash.
Either 6 or 10 seconds, at 768p or 1080p, with 1080p capped at 6 seconds.
An image-to-video variant that is roughly 2.5 times faster and about half the cost, made for quick iteration and batch production.
On Apiframe it is credit-based and priced per clip: the Fast tier starts at 33 credits ($0.33) for a 6-second 768p clip, and standard Hailuo 2.3 starts at 48 credits ($0.48), so you only pay for what you generate.
Through Apiframe, as well as the Hailuo app, the MiniMax API, and major hosting partners.
Still have questions?
Get your API key and integrate Hailuo 2.3 in minutes — Pay-as-you-go.
Questions? Join our Discord or contact sales.