Skip to navigation
Authors and ModelsOpenMOSS

MOSS-Image Turbo

MOSS-Image Turbo
OpenMOSS · Image Generation
POST /v1/images/generations

OpenMOSS text-to-image model that renders accurate English and Chinese text in signs, posters, and layouts, with aspect ratio and seed controls.

At a glance

FieldValue
Model idmoss-image-turbo
Model release date2026-10-16
Input modalitiesText
Output modalitiesImage
Context window-
Weight precisionINT8
Featuresimage_generation, text_rendering, multilingual_text, seed_control
Native inferenceYes
NewYes
Supported endpointsPOST /v1/images/generations

Pricing

ChargeSpecRate
Image generationper image$0.015

Example request

curl https://api.empiriolabs.ai/v1/images/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "moss-image-turbo", "prompt": "a misty forest at dawn", "size": "1024x1024"}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Text description of the image to generate, up to 4,000 characters.
aspect_ratioenumno"1:1"Output aspect ratio. Used when size, width and height are unset. · Allowed: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
sizestringno-Explicit WIDTHxHEIGHT override. Each side is a multiple of 16 from 512 to 2048 pixels, and width x height is at most 1,048,576 pixels. Leave unset to use aspect_ratio.
widthnumberno-Output width in pixels, a multiple of 16. Set width and height together. Width x height must be at most 1,048,576 pixels. · Range: 512 – 2048
heightnumberno-Output height in pixels, a multiple of 16. Set width and height together. Width x height must be at most 1,048,576 pixels. · Range: 512 – 2048
seednumberno-Random seed. Leave unset for a random one; each image returns the seed it used. · Range: 0 – 2147483647
num_imagesnumberno1How many images to generate (1-4). · Range: 1 – 4
formatenumno"webp"Image file codec for the generated output. · Allowed: webp, png, jpg, jpeg
response_formatenumno"url"Return a signed media URL by default, or base64 JSON when requested. · Allowed: url, b64_json
return_base64booleannofalseCompatibility alias for response_format=b64_json.

Notes

Generates images from text, with accurate English and Chinese text in signs, posters, labels, and layouts.

Input

  • A text prompt of up to 4,000 characters. Image inputs, negative prompts, and LoRA adapters are not supported.
  • Size from aspect_ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3), from size as WIDTHxHEIGHT, or from width and height. Each side is a multiple of 16 from 512 to 2,048 pixels, and width x height is at most 1,048,576 pixels. The default is 1024x1024.
  • Up to 4 images per request with num_images.

Output

  • WebP by default, or PNG or JPEG with format.
  • A signed URL by default, or base64 with response_format set to b64_json.
  • Each image carries the seed it used.

Content safety

Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

Weights

  • INT8.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/moss-image-turbo.