/api/v1/images/generations with model: moss-image and a prompt. Every job returns a single PNG at a flat price per resolution tier.MOSS-Image API for Layout and Long Text
MOSS-Image is an open-weight text-to-image model from OpenMOSS built for layout and long text: posters, menus, signs and infographics with accurate English and Chinese lettering. POST to
Get API Key
Text-Heavy Images from One Prompt
Long text rendered as written
Put the exact words in quotes and they are rendered in the image as written, in English, Chinese or both. Prompts of up to 4,000 characters are accepted, which leaves room for dense layouts such as menus, price lists and event posters.
Eight aspect ratios at two sizes
Text to image accepts
1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9 and 21:9, at about 1 megapixel (1K) or about 4 megapixels (2K).
model and prompt are required; everything else is optional.
MOSS-Image Request Fields and Limits
model
Always
moss-image.prompt
Required, up to 4,000 characters. Text in quotes is rendered as written, in English or Chinese.
ratio
auto (default, means 1:1), 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9.image_size
1K (default, about 1 megapixel) or 2K (about 4 megapixels). Case-insensitive; also the price tier.seed, custom_callback_url
seed: 0 to 2147483647 for more reproducible results. custom_callback_url: optional HTTPS URL for status callbacks.Flat per image by resolution tier.
MOSS-Image API Pricing
1K: 1 token ($0.02) per image
About 1 megapixel. This is the default
image_size.2K: 4 tokens ($0.08) per image
About 4 megapixels.
No extra charge for long prompts
A 4,000-character prompt at 1K costs the same 1 token ($0.02) as a one-line prompt.
Failed jobs are refunded
Tokens are deducted when the task is accepted and returned automatically if the generation fails.
Integrate the MOSS-Image API
2
2. Write the prompt
Describe the layout and quote every word you want in the image, in English, Chinese or both.
3
3. Submit
POST
{"model": "moss-image", "prompt": "…", "ratio": "16:9", "image_size": "1K"} to /api/v1/images/generations and store img_uuid. 4
4. Download the PNG
Poll
GET /api/v1/jobs/detail or use your callback, and save the PNG from json[0].value within 24 hours.Images where the words matter as much as the picture.
What Developers Build with MOSS-Image
Menus and price boards
Generate cafe menus, price lists and signage with every item and price spelled out as written.
Bilingual posters
Produce event posters and social graphics that mix English and Chinese headlines in one layout.
Infographics and slides
Turn structured content into labeled diagrams, charts and slide visuals from a long prompt.
Packaging and label mock-ups
Generate product labels, tags and packaging fronts with the exact brand copy and ingredients you specify.
Endpoint, text rendering, limits and pricing.
MOSS-Image API FAQ
What is the MOSS-Image API endpoint?
POST https://api.goenhance.ai/api/v1/images/generations with model: moss-image.
How much does an image cost?
1 token ($0.02) at 1K and 4 tokens ($0.08) at 2K.
How do I get exact text in the image?
Put the words in quotes in the prompt, for example a sign that reads "OPEN 24 HOURS". English and Chinese can be mixed. Text you do not specify may come out as filler.
Can I edit an existing image?
Not yet. MOSS-Image on GoEnhance is text to image only, and requests with image_list are rejected before any tokens are charged.
How long does a job take?
The docs give about 15 to 20 seconds of processing at 1K and about 1 to 2 minutes at 2K, plus queue time. Use polling or custom_callback_url.