Skip to main content

Overview

FLUX 3 Image generates images from text and edits or combines reference images. Each task returns one image. Choose a resolution and output format, submit a task, then poll for the result or receive a webhook callback.

Endpoint and authentication

Base URL:
Include your APIXO API key in every request:
Submit requests also require Content-Type: application/json.

Copy-paste async quickstart

Submit a text-to-image task:
Successful submission:
Save data.taskId and query the status endpoint. A successful submission means the task was accepted; check data.state to determine the final outcome.

Poll for result

While the task is running, data.state is processing. Continue polling until it becomes success or failed. Success response:
resultJson is a JSON string. Parse it before reading the image URL:
Failure response:
A status response with code: 200 can still describe a failed task. Use data.state, failCode, and failMsg to handle task failures.

Image-to-image request

Provide 1-10 reference images in image_urls. Their order is preserved, so refer to them as image 1, image 2, and so on in the prompt.
Replace the example URLs with public, directly fetchable image URLs. Each reference image must be at least 256 pixels on both sides and contain no more than 4,000,000 pixels (width * height). When aspect_ratio is omitted or blank in image-to-image mode, the output follows the first reference image’s aspect ratio.

Parameters

string
default:"async"
Result delivery mode. Supported values: async, callback. Use async for status polling or callback for webhook delivery.
string
Required when request_type is callback. Provide a public HTTPS endpoint that accepts POST requests. See Webhooks.
object
required
FLUX 3 Image input parameters.

Status response fields

All fields below are inside data.

Webhook callback mode

Set request_type to callback and provide callback_url:
See Webhooks for receiver setup and delivery handling.

Billing

Both modes generate one image per task and use the same resolution-based prices. The number of reference images does not add a separate charge. See Pricing for current prices.

Latency and polling

Generation time varies with resolution, prompt complexity, reference images, and queue load. A 4K task can take several minutes. If a request is rate-limited, reduce concurrency and retry with backoff. Keep the original taskId when querying an accepted task.

Errors and troubleshooting

  • Check that mode and a non-empty prompt are present.
  • For image-to-image, provide 1-10 valid reference URLs and respect the per-image dimension and pixel limits.
  • Use one of the documented aspect ratios, resolution tiers, and output formats.
  • Inspect data.state even when the status endpoint returns code: 200.
  • When a task fails, use failCode and failMsg to decide whether to change the input before submitting another task.
See Error Codes for authentication, balance, rate-limit, and task failure handling.