alibaba/
Text to ImageAlibaba's Z-Image Base is the standard, non-Turbo Z-Image model, using more steps and guidance for careful renders. Choose it when detail outweighs turnaround in portraits, illustration and magazine-style scenes, with negative prompts, guidance 1-20, up to 50 steps, custom sizes and seeds.
More settings (7)
$0.01 / megapixel · billed by each image's actual pixels
A warm, cinematic photograph of an elderly grandmother knitting a soft red wool scarf in an armchair beside a tall window. Late-afternoon golden light falls across her silver hair, reading glasses and wrinkled hands. Next to her stands an empty wooden chair with a folded cardigan draped over the back and a cup of tea going cold on a small side table. Lace curtains, potted geraniums on the windowsill, dust motes floating in the light, quiet nostalgic mood, shallow depth of field, 50mm lens, natural film grain.
Pricing
Unit price $0.01 / megapixel
Billed by the actual pixels of each image; larger sizes and more images cost more. 1024×1024 is about 1 megapixel.
Each request temporarily reserves $0.02; you are charged for actual usage, usually within a minute: any unused amount is released and any usage above it is charged to your balance, even if that takes it below zero; while your balance is below zero, new requests are paused until a top-up covers it.
Failed generations are not charged.
API
Submit generation requests with this model ID.
/v1/model-tasksalibaba/z-image-base/text-to-image{
"model": "alibaba/z-image-base/text-to-image",
"input": {
"prompt": "A warm, cinematic photograph of an elderly grandmother knitting a soft red wool scarf in an armchair beside a tall window. Late-afternoon golden light falls across her silver hair, reading glasses and wrinkled hands. Next to her stands an empty wooden chair with a folded cardigan draped over the back and a cup of tea going cold on a small side table. Lace curtains, potted geraniums on the windowsill, dust motes floating in the light, quiet nostalgic mood, shallow depth of field, 50mm lens, natural film grain.",
"acceleration": "regular",
"guidance_scale": 4,
"image_size": "landscape_4_3",
"negative_prompt": "blurry, low quality, distorted hands, extra fingers, oversaturated, cartoon",
"num_images": 1,
"num_inference_steps": 28,
"output_format": "png"
}
}Input schema
| Parameter | Type | Requirement | Default |
|---|---|---|---|
| prompt | string | Required | — |
| acceleration | string | Optional | regular |
| guidance_scale | number | Optional | 4 |
| image_size | object | string | Optional | landscape_4_3 |
| negative_prompt | string | Optional | |
| num_images | integer | Optional | 1 |
| num_inference_steps | integer | Optional | 28 |
| output_format | string | Optional | png |
| seed | integer | Optional | — |
Response
The API returns a result or a pollable asynchronous task. See the examples and Schema below for the response mode and result fields.
Code examples
Async submission returns a task ID. Poll until status is completed, then retrieve the generated content from the result. Get your API key in the console.
# Use a new directory for each new generation. Rerunning here continues this task.
set -eu
test -s model-task-id.txt || python3 -c "import uuid; print(uuid.uuid4())" > model-task-id.txt
REQUEST_ID=$(cat model-task-id.txt)
# Idempotent: resending the same bytes with the same ID never charges twice.
curl --fail-with-body --retry 3 --retry-connrefused --request POST 'https://api.musespan.com/v1/model-tasks' \
--header "Authorization: Bearer $MUSESPAN_API_KEY" \
--header "X-Request-Id: $REQUEST_ID" \
--header "Content-Type: application/json" \
--data '{"model":"alibaba/z-image-base/text-to-image","input":{"prompt":"A warm, cinematic photograph of an elderly grandmother knitting a soft red wool scarf in an armchair beside a tall window. Late-afternoon golden light falls across her silver hair, reading glasses and wrinkled hands. Next to her stands an empty wooden chair with a folded cardigan draped over the back and a cup of tea going cold on a small side table. Lace curtains, potted geraniums on the windowsill, dust motes floating in the light, quiet nostalgic mood, shallow depth of field, 50mm lens, natural film grain.","acceleration":"regular","guidance_scale":4,"image_size":"landscape_4_3","negative_prompt":"blurry, low quality, distorted hands, extra fingers, oversaturated, cartoon","num_images":1,"num_inference_steps":28,"output_format":"png"}}'
# Poll every 5 seconds for up to 25 minutes until status is completed or failed.
# Still queued (with queue_position) 5 minutes after submission: failed with queue_timeout, not charged.
# No result 15 minutes after acceptance (or no confirmation 15 minutes after submission): failed with generation_timeout, not charged.
# Any failure is final: generate again in a new directory (a new X-Request-Id).
# A 404 means the POST did not arrive: rerun this script to resend it with the same ID.
curl --fail-with-body 'https://api.musespan.com/v1/model-tasks/'"$REQUEST_ID"'' --header "Authorization: Bearer $MUSESPAN_API_KEY"