FLUX 3 API - APIXO

Overview

FLUX 3 is a Black Forest Labs video model for generating short videos from text, animating one or two image frames, or extending an existing short video. Use this page when you are ready to call the API after trying FLUX 3 in the APIXO playground.

Capability	Value
Model ID	`flux-3`
Modes	`text-to-video`, `image-to-video`, `video-extend`
Prompt length	1-5000 characters
Duration	5-20 seconds
Resolutions	`720p`, `1080p`
Aspect ratios	`21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
Image-to-video sources	1 image URL, or 2 image URLs for start and end frames
Video extension source	Exactly 1 public MP4 URL, up to 50 MB and 15 seconds
Audio	Enabled by default with `sound: true`
Output	MP4 video URLs in `resultJson.resultUrls`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/flux-3`	Submit a video generation task
`GET`	`/statusTask/flux-3?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 text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/flux-3" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic macro shot of glass sculptures forming from liquid light",
      "duration": 5,
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "sound": true
    }
  }'

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/flux-3?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/flux-3.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965680929,
    "costTime": 70000
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "INVALID_PARAMETER",
    "failMsg": "One or more input parameters are invalid.",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

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

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a wide cinematic desert highway at sunrise, gentle aerial camera movement",
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "sound": true
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "animate the portrait with a subtle smile and soft studio camera drift",
    "image_urls": [
      "https://example.com/source.png"
    ],
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "sound": true
  }
}

Image-to-video with start and end frames

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "transition smoothly from the empty room into the decorated final scene",
    "image_urls": [
      "https://example.com/start-frame.png",
      "https://example.com/end-frame.png"
    ],
    "duration": 10,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "sound": false
  }
}

Video extend

{
  "request_type": "async",
  "input": {
    "mode": "video-extend",
    "prompt": "continue the camera move forward as the scene opens into a bright atrium",
    "video_urls": [
      "https://example.com/source.mp4"
    ],
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "sound": true
  }
}

Parameters

string

default:"async"

Result delivery mode. Omit this field or use async for polling with statusTask, or use callback for webhook delivery.

string

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

object

required

FLUX 3 input parameters.

Show properties

string

required

Generation mode. Supported values: text-to-video, image-to-video, video-extend.

string

required

Text prompt describing the desired video. Supports 1-5000 characters. Empty prompts are rejected.

integer|string

default:"5"

Output duration in seconds. Supports integers or integer strings from 5 through 20. Decimal values are not valid.

string

default:"720p"

Output resolution. Supported values: 720p, 1080p.

string

default:"9:16"

Output aspect ratio. Supported values: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16.

boolean

default:"true"

Whether to generate synchronized audio. Supported values: true, false. Audio does not add a separate charge.

string[]

Reference image URLs. Required for image-to-video. Provide 1 public image URL, or 2 public image URLs where the first URL is the start frame and the second URL is the end frame.

string[]

Source video URLs. Required for video-extend. Provide exactly 1 public MP4 URL. The source video must be no larger than 50 MB and no longer than 15 seconds.

Mode options

Mode	Required media	Use case
`text-to-video`	None	Generate a video from a prompt
`image-to-video`	`image_urls` with 1 or 2 URLs	Animate one image, or generate motion between start and end frames
`video-extend`	`video_urls` with exactly 1 MP4 URL	Continue an existing short video

Response format

Submit task response

POST /generateTask/flux-3 returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: pending, processing, processing_r2, success, or failed.

string

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

string

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

string

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

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds 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/flux-3" \
  -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": "image-to-video",
      "prompt": "turn the product photo into a premium reveal shot with slow camera motion",
      "image_urls": [
        "https://example.com/product.png"
      ],
      "duration": 5,
      "resolution": "720p",
      "aspect_ratio": "9:16",
      "sound": true
    }
  }'

Callback delivery uses the same final payload shape as the status response. See Webhooks for delivery requirements and retry behavior.

Billing

FLUX 3 is billed per output second. The selected resolution determines the per-second unit price, and duration determines the billable seconds. text-to-video, image-to-video, start/end-frame image-to-video, and video-extend use the same resolution-based pricing.

Resolution	APIXO price	Example total
`720p`	`$0.17 / second`	5s: `$0.85`
`1080p`	`$0.29 / second`	10s: `$2.90`

Formula:

total cost = duration * resolution unit price

Audio generation with sound: true does not add a separate charge. For the latest published pricing, see Pricing.

Latency and polling

Actual latency may vary by prompt complexity, selected mode, media accessibility, duration, resolution, and current queue load.

Request shape	Typical generation time	Recommended first poll	Poll interval
`5-8` second clip	60s-120s	60s after task creation	5s-10s
`9-15` second clip	120s-240s	90s after task creation	10s
`16-20` second clip	240s+	120s after task creation	10s-15s

For production video workloads, use callback mode to avoid frequent polling while generation is still running.

For image-to-video, use image_urls with either 1 or 2 URLs. Two URLs represent the start and end frames in order. For video-extend, use one public MP4 URL. Keep the source file under 50 MB and at or below 15 seconds.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing `mode`, missing `prompt`, invalid media input, invalid `duration`, invalid `resolution`, or invalid `aspect_ratio`	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`	This API key cannot access the model	Check account permissions
`404`	Task not found when polling	Check the `taskId`
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Internal error or unknown task failure	Retry with backoff or contact support if it persists
`502`	Generation service or network error	Retry with backoff
`503`	Service temporarily unavailable	Retry later
`504`	Generation timeout	Retry later or use callback mode for long-running jobs

Validation notes

Parameter	Backend behavior
`input.mode`	Required. Values are trimmed and lowercased. Must be `text-to-video`, `image-to-video`, or `video-extend`.
`input.prompt`	Required string. Must not be empty and must not exceed 5000 characters.
`input.duration`	Optional. Defaults to `5`. Accepts an integer or an integer string from `5` through `20`; decimals are rejected.
`input.resolution`	Optional. Defaults to `720p`. `720p` and `1080p` are accepted after trimming and lowercasing.
`input.aspect_ratio`	Optional. Defaults to `9:16`. Must be one of `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` when provided.
`input.sound`	Optional. Defaults to `true`. Must be a boolean value.
`input.image_urls`	Required for `image-to-video`. Must contain 1 or 2 non-empty public image URLs.
`input.video_urls`	Required for `video-extend`. Must contain exactly 1 non-empty public MP4 URL; the source must be no larger than 50 MB and no longer than 15 seconds.

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​Image-to-video with start and end frames

​Video extend

​Parameters

​Mode options

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Validation notes

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Image-to-video with start and end frames

Video extend

Parameters

Mode options

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Validation notes

Related links