Skip to content

Alibaba · fal.ai · Image edit

Qwen Image 3

Qwen Image 3 (Alibaba), image edit, served by fal.ai. The OpenAPI schema for the alibaba/qwen-image-3/edit queue. Price: $0.04 per image at 1K resolution; preset sizes only.

$0.04 / unitfal.aiImagefal/qwen-image-3-editListed

Activation pending; your agent will see it as unavailable until then.

Use this tool with your agent

Give this to your agent
Use my connected Agentik MCP server. I want to use the tool fal/qwen-image-3-edit (Qwen Image 3 (Alibaba), image edit). Call inspect_tool with {"tool_id": "fal/qwen-image-3-edit"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/qwen-image-3-edit" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.
Show the prompt

Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.

Parameters

NameTypeRequiredDescription
num_imagesintegerNoThe number of images to generate.
image_sizestringNoThe size of the generated image. If not provided, the model determines the resolution automatically. Total number of pixels must be between 512x512 and 2048x2048. Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9.
enable_prompt_expansionbooleanNoEnable automatic LLM prompt rewriting for better results.
seedintegerNoRandom seed for reproducibility (0-2147483647).
promptstringYesText prompt describing the desired edit. Supports Chinese and English. Max 5000 characters.
image_urlsstring[]YesReference images for editing (1-3 images required). Order matters: reference as 'image 1', 'image 2', 'image 3' in prompt. Resolution: 384-2048px each dimension. Max size: 10MB each. Formats: JPEG, JPG, PNG (no alpha), WEBP.
negative_promptstringNoContent to avoid in the generated image. Max 500 characters.
output_formatstringNoThe format of the generated image. Options: jpeg, png, webp.
enable_safety_checkerbooleanNoEnable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.

How your agent calls it

First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:

{
  "tool_id": "fal/qwen-image-3-edit",
  "input": {
    "prompt": "make the cube blue, keep everything else",
    "image_urls": [
      "https://storage.googleapis.com/falserverless/example_outputs/nano-banana-2-t2i-output.png"
    ],
    "num_images": 1,
    "image_size": "square"
  }
}

Price and billing

Price
$0.04 / unit
Model
Per unit
Detail
The provider’s price, with no markup. Billed for measured usage.
  • The provider’s price, 0% markup.
  • One prepaid balance for every provider; your agent sees the price before it runs.
  • Pay for measured usage; unused reservations are released.