Hailuo 2.3 Fast API

Hailuo 2.3 Fast image-to-video API with standard and pro modes

Overview

Hailuo 2.3 Fast is an image-to-video model for turning one source image into a short generated video. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	hailuo-2-3-fast
Modes	standard-image-to-video, pro-image-to-video
Input type	Image-to-video only
Reference images	Exactly 1 image URL
Standard duration	6 or 10 seconds
Pro duration	Fixed 6 seconds
Output resolution	Standard: 768p; Pro: 1080p
Result type	Video URL in resultJson.resultUrls

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
POST	/generateTask/hailuo-2-3-fast	Submit a generation task
GET	/statusTask/hailuo-2-3-fast?taskId={taskId}	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a standard image-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/hailuo-2-3-fast" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "standard-image-to-video",
      "prompt": "animate this character portrait with a gentle cinematic camera move",
      "image_urls": [
        "https://example.com/input.jpg"
      ],
      "duration": 6
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/hailuo-2-3-fast?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965730929,
    "costTime": 120000
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "SensitiveContent",
    "failMsg": "Content violates provider policy, please adjust the prompt",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Standard image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "standard-image-to-video",
    "prompt": "animate this still image with smooth parallax and lighting changes",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "duration": 10
  }
}

Pro image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "pro-image-to-video",
    "prompt": "animate this image into a high-energy camera move",
    "image_urls": [
      "https://example.com/input.jpg"
    ]
  }
}

Parameters

request_type · string · default: "async" · required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url · string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

input · object · required

Hailuo 2.3 Fast input parameters.

Show properties

mode · string · required

Generation mode. Supported values: standard-image-to-video, pro-image-to-video. Use the exact lowercase value; text-to-video modes are not supported.

prompt · string · required

Text prompt describing the desired motion and scene. Must be a non-empty string and no more than 2,000 UTF-8 bytes; whitespace-only prompts are rejected.

image_urls · string[] · required

Source image URLs. Must contain exactly one non-empty string. The image should be a public JPG, JPEG, or PNG URL, no larger than 20 MB, with an aspect ratio greater than 2:5 and less than 5:2, and a short side greater than 300 px.

duration · integer|string

Required for standard-image-to-video. Supported values: 6, 10, "6", or "10". The backend normalizes valid values to an integer for generation and billing. Ignored for pro-image-to-video, which always outputs a 6-second video.

Hailuo 2.3 Fast only supports image-to-video. If you need text-to-video, use a different Hailuo model that explicitly supports that mode.

Response format

Submit task response

POST /generateTask/hailuo-2-3-fast returns a task ID when the task is accepted:

code · integer

API status code. 200 means the task was accepted.

message · string

Human-readable status message.

data.taskId · string

Unique task identifier used with the status endpoint.

Status response fields

taskId · string

Unique task identifier.

state · string

Current task state: processing, success, or failed.

resultJson · string

JSON string containing the generated video URLs. Present when state is success.

failCode · string

Machine-readable failure code. Present when state is failed.

failMsg · string

Human-readable failure message. Present when state is failed.

createTime · integer

Task creation timestamp in Unix milliseconds.

completeTime · integer

Task completion timestamp in Unix milliseconds. Present after completion when available.

costTime · integer

Processing duration in milliseconds. Present after completion when available.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/hailuo-2-3-fast" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "pro-image-to-video",
      "prompt": "animate this product photo with a polished studio camera move",
      "image_urls": [
        "https://example.com/input.jpg"
      ]
    }
  }'

See Webhooks for delivery requirements and retry behavior.

Billing

Hailuo 2.3 Fast billing depends on the selected mode. Standard mode is billed by output duration; pro mode is billed per task.

Mode	Unit	APIXO price	Billable amount
standard-image-to-video	Per output second	$0.032 / second	duration * $0.032
pro-image-to-video	Per task	$0.33 / use	$0.33

For current route and market comparison pricing, see Pricing.

Latency and polling

Video generation is asynchronous. Actual latency may vary by input image, prompt complexity, current queue load, and storage transfer time.

Mode	Output duration	Recommended first poll	Poll interval
standard-image-to-video	6 or 10 seconds	30s after task creation	10s
pro-image-to-video	Fixed 6 seconds	30s after task creation	10s

costTime is returned in milliseconds after completion when timing data is available. Keep polling while state is processing.

For production workloads, use callback mode to avoid frequent polling on long-running video tasks.

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
400	Invalid request body, missing required field, unsupported mode, invalid duration, or invalid input URL	Fix the request before retrying
401	Missing or invalid API key	Check the Authorization header
402	Insufficient balance or quota	Add balance or switch account/key
403	Key or route cannot access the model	Check permissions and route strategy
429	Rate limit or concurrency limit reached	Retry with exponential backoff
500	Server error or unmapped upstream failure	Retry with backoff
502	Upstream provider error	Retry with backoff
504	Upstream timeout	Retry or use callback mode for long-running jobs

Task failure codes

Failure codes are mapped from upstream task errors, so exact values can vary. Common examples include:

Fail code	Meaning	What to do
PromptInvalid	Prompt was invalid or rejected	Rewrite the prompt and retry
SensitiveContent	Prompt or media violated provider policy	Change the prompt or input image
NSFW	Input or output was flagged as NSFW	Use different content
ProhibitedContentDetected	Prohibited content was detected	Change the prompt or input image
ImageFormatIncorrect	Image format or upload validation failed	Use a public JPG, JPEG, or PNG URL
InvalidImageSize	Image dimensions or size were invalid	Check aspect ratio, short side, and file size
RateLimited	Upstream provider rate limit was reached	Retry with exponential backoff
Timeout	Upstream provider timed out	Retry, simplify the prompt, or use callback mode
InsufficientBalance	Provider-side balance or quota was insufficient	Retry later or contact support
Unknown error	Upstream failure was not mapped to a known code	Retry with backoff; contact support if it persists

Request checks

• Send exactly one image_urls item.
• Use only standard-image-to-video or pro-image-to-video.
• Include duration only when you need standard mode; pro mode ignores it.
• Use duration as 6, 10, "6", or "10" for standard mode.
• Use a public, directly fetchable JPG, JPEG, or PNG image URL.

See Error Codes for the full error reference.

Related links

• Generation API Overview
• Video Models
• Generate Task
• Status Task
• Webhooks
• Error Codes
• Parameter Specification
• Routing Strategies
• Try Hailuo 2.3 Fast in the APIXO Playground
• Pricing