Qwen Image 3.0

Image GenerationImage Editing1K and 2K at One Rate

Qwen Image 3.0 generates images from a prompt and edits existing ones with up to three reference images. Output is 1K or 2K at fifteen aspect ratios, and text-to-image costs the same at either resolution, so drafts and finals run at one predictable rate.

Workflows

Text-to-Image / Image-to-Image

APIXO Price

From $0.03 / Image

Resolution

1K / 2K

Reference Images

Up to 3

Aspect Ratios

15 Presets

Loading workspace...

Qwen Image 3.0 Model API Rate Structure

Billed per successfully generated image, with one image per accepted task. Text-to-image costs the same at 1K and 2K; in image-to-image each reference image adds $0.003. Failed tasks are refunded.

Text-to-image

Resolution

APIXO price

$0.03

Text-to-image

Resolution

APIXO price

$0.03

Image-to-image · 1 reference

Resolution

APIXO price

$0.033

Image-to-image · 2 references

Resolution

APIXO price

$0.036

Image-to-image · 3 references

Resolution

APIXO price

$0.039

Image-to-image · 1 reference

Resolution

APIXO price

$0.033

Image-to-image · 2 references

Resolution

APIXO price

$0.036

Image-to-image · 3 references

Resolution

APIXO price

$0.039

Workflow	Resolution	APIXO price
Text-to-image	1K	$0.03
Text-to-image	2K	$0.03
Image-to-image · 1 reference	1K	$0.033
Image-to-image · 2 references	1K	$0.036
Image-to-image · 3 references	1K	$0.039
Image-to-image · 1 reference	2K	$0.033
Image-to-image · 2 references	2K	$0.036
Image-to-image · 3 references	2K	$0.039

Checking API access...

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

Create task

POSThttps://api.apixo.ai/api/v1/generateTask/qwen-image-3-0

Poll status

GEThttps://api.apixo.ai/api/v1/statusTask/qwen-image-3-0?taskId={taskId}

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose the generation workflow supported by this model.text-to-image · image-to-image

promptrequired

Typestring

Describe the subject, composition, style, lighting, and details you want in the final image.

aspect_ratiorequired

Typeselect

Choose the output frame ratio.auto · 1:1 · 1:2 · 2:1 · 1:3 · 3:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 9:21 · 21:9

resolutionrequired

Typeselect

Choose the output resolution tier. Higher tiers can cost more.1k · 2k

enable_prompt_expansionoptional

Typeboolean

Let the model enrich a short prompt with additional detail before generating. Enabled by default.

seedoptional

Typetext

Use -1 for a random seed, or a whole number from 0 to 2147483647 to keep framing closer between runs.

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose the generation workflow supported by this model.text-to-image · image-to-image
`prompt`	string	required	Describe the subject, composition, style, lighting, and details you want in the final image.
`aspect_ratio`	select	required	Choose the output frame ratio.auto · 1:1 · 1:2 · 2:1 · 1:3 · 3:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 9:21 · 21:9
`resolution`	select	required	Choose the output resolution tier. Higher tiers can cost more.1k · 2k
`enable_prompt_expansion`	boolean	optional	Let the model enrich a short prompt with additional detail before generating. Enabled by default.
`seed`	text	optional	Use -1 for a random seed, or a whole number from 0 to 2147483647 to keep framing closer between runs.

File parameters (URL arrays)

image_urls[ mode=image-to-image ]Upload one to three reference images for image-to-image. Each additional reference raises the per-image rate.

Only in mode=image-to-image

Example (cURL)

1curl -X POST "https://api.apixo.ai/api/v1/generateTask/qwen-image-3-0" \2  -H "Authorization: Bearer YOUR_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "request_type": "async",6    "input": {7      "mode": "text-to-image",8      "prompt": "a clean editorial infographic poster about how cold brew works",9      "aspect_ratio": "4:3",10      "resolution": "2k",11      "enable_prompt_expansion": true,12      "seed": -113    }14  }'

Full API documentation

Capabilities

Generate, edit, and frame from a single seven-field request

Text-to-Image Generation

Describe a scene, layout, or poster and receive one finished image per accepted task. No batch-count field is exposed, so every request maps to exactly one billable output.

Instruction-Guided Editing

Switch the mode field to image-to-image and describe the change in the same prompt field. There is no mask parameter; the instruction and the supplied images carry the edit.

Up to Three References

Image-to-image accepts one to three publicly fetchable image URLs, letting you combine a subject, an environment, and a style cue in one request instead of chaining separate edits.

Flat Resolution Pricing

This route currently charges the same rate for 1K and 2K in both workflows. Explore at whichever tier suits the review and keep the cost per image unchanged.

Fifteen Framing Presets

Choose from 15 documented ratios spanning square, portrait, landscape, and extreme formats such as 21:9, 9:21, 1:3, and 3:1 for banners and vertical strips.

Prompt Expansion and Seeds

Prompt expansion is on by default and enriches short briefs before generation. Turn it off to keep your wording verbatim, and set a seed from 0 to 2147483647 to keep framing closer between runs.

APIXO Workflows

Create from a prompt or edit from your own images

Text-to-Image

Send a prompt and pick framing and resolution. Aspect ratio defaults to 1:1 and resolution defaults to 1K. Both resolutions cost $0.03 per image, so the tier is a quality choice rather than a pricing one.

Create from text

Image-to-Image

Supply one to three public image URLs plus an instruction of up to 800 characters. Each reference raises the rate by $0.003 per image. Leave the aspect ratio unset and the result follows the first input image.

Edit with references

APIXO Configuration

Request fields and output controls

Verified options available through APIXO’s Qwen Image 3.0 route.

Up to 800 Characters

Prompt Length (Editing)

1 Image per Task

Output Count

1–3 URLs

Reference Images

15 Presets

Aspect Ratios

1K / 2K

Resolution

Async / Callback

Delivery

Production Uses

Where a flat-rate image route fits into a workflow

Volume Drafting

Explore Many Directions at One Rate

Because 1K and 2K cost the same on this route, an exploration pass costs the same per image as a final pass. Run wide variation sets without tracking which ones were rendered at which tier.

Editorial Layouts

Posters, Explainers, and Structured Graphics

Prompt for headlines, numbered steps, and caption pairs and let the model render the type as part of the image. Proofread every rendered word before publishing; spelling and numerals are not guaranteed.

Reference Compositing

Combine a Subject, a Scene, and a Style Cue

Send up to three references in one image-to-image request instead of chaining edits. Each added reference raises the rate, so start with one and add more only when the instruction needs them.

Format Delivery

Cover Banners, Feeds, and Vertical Strips

The 15 presets reach past the common set to 21:9, 9:21, 1:3, and 3:1, so wide headers and tall strips come from the same request rather than a downstream crop.

Notes & FAQ

Request fields, framing behaviour, and billing boundaries

Implementation Notes

Every accepted task returns one image. APIXO exposes no batch-count field, so the price shown for a configuration is the price of that request.

Text-to-image is $0.03 per image at 1K and at 2K. Image-to-image ranges up to $0.039 per image, driven by how many reference images the request carries.

Each reference image adds $0.003 per generated image, and the route accepts at most 3. References must be publicly fetchable URLs.

Leaving the aspect ratio unset in image-to-image keeps the first input image’s ratio. Text-to-image falls back to 1:1 when no ratio is sent.

Prompt expansion defaults to on. The seed field accepts -1 for random or a whole number from 0 to 2147483647; matching seeds bring runs closer together but do not guarantee identical output.

APIXO reserves the rate for the selected configuration when a task is accepted and settles it on success. Failed tasks are refunded.

Frequently Asked Questions

Text-to-image is $0.03 per generated image. Image-to-image starts higher and rises with the number of reference images, up to $0.039 per image with three references. Billing is per successfully generated image.

Not on this route. Both resolutions are billed at the same rate in text-to-image and in image-to-image, so the tier is purely a quality decision. Published rates can change, and the pricing table above always reflects the current catalog.

One to 3, supplied as publicly fetchable URLs, and only in image-to-image mode. Each one adds $0.003 per generated image. Text-to-image ignores the field entirely.

The result keeps the ratio of the first input image. That is documented behaviour rather than a missing value, so omit the field when you want the edit to preserve the source framing, and set it explicitly when you want to reframe.

Pro is a separate APIXO route with its own request endpoint and its own rates, where 2K costs noticeably more than 1K. This route keeps one rate across both resolutions, which suits iteration and volume work. Compare the two pricing tables before committing a pipeline.

Explore Other Models

Discover more AI models for your next creative workflow

View all models

Alibaba

Qwen Image 3.0 Pro

Qwen Image 3.0 Pro is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.