Alibaba Qwen Image 3.0 Generate

36 credits/call
ae_alibaba_qwen_image_3_0_generate

Qwen Image 3.0 text to image. Use when a prompt should produce a new image.

Image
36 credits/call

Pricing

36 credits/call
ConditionCharge
Each call36 credits/call

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedintegerNoRandom seed for reproducibility (-1 for random, 0-2147483647 for specific seed)—
request_body.promptstringYesText prompt describing the desired image, supports Chinese and English (max 800 characters)—
request_body.resolutionenum (1k | 2k)NoOutput resolution tier. All tiers are billed at the same price.1k
request_body.aspect_ratioenum (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)NoThe aspect ratio of the generated image. Defaults to 1:1.1:1
request_body.enable_prompt_expansionbooleanNoWhether to enable intelligent prompt expansionfalse

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_alibaba_qwen_image_3_0_generate' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "4:3",
      "prompt": "Minimal isometric illustration of a secure data pipeline, glowing nodes connected from a cloud server to ground receiving stations, thin emerald green lines, cool grey and white palette, pure white background, soft shadows, clean technical diagram style, no text, no letters, no watermark",
      "resolution": "1k"
    }
  }
}'
Response exampleresponse.json
JSONPartial content
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "add33ccb-e275-4449-989f-b5d99c9f37f3"
}

This example shows part of the response. Copied content is valid JSON.