Models
Models
Every model takes the same task request. Models on our GPUs are uncensored and pass every image through our output safety check; models from other publishers run on the publisher's API, under its moderation. GET /v1/models returns the same details, with JSON Schemas for the inputs.
FLUX 3 Image Klein
flux-3-klein
Black Forest Labs' step-distilled FLUX 3 Klein on VelvetAPI's own GPUs: text to image, and edits from up to ten of your own generated images.
$0.01 per imageOur GPUsText to imageImage editing
Z-Image Turbo
z-image-turbo
Tongyi-MAI's 8-step distilled Z-Image Turbo on VelvetAPI's own GPUs: fast, photorealistic text to image.
$0.006 per imageOur GPUsText to image
Qwen Image 3.0
qwen-image-3.0
Alibaba's Qwen Image 3.0 through Alibaba Cloud Model Studio: text to image, or edits combining up to three of your images, with strong text rendering. Model Studio's content moderation applies, so explicit requests are refused.
$0.035 per imagePublisher's APIText to imageImage editing
Qwen Image 3.0 Pro
qwen-image-3.0-pro
Alibaba's flagship Qwen Image 3.0 Pro through Alibaba Cloud Model Studio: finer detail and text than Qwen Image 3.0, up to 2.25 megapixels. Model Studio's content moderation applies, so explicit requests are refused.
$0.045 per imagePublisher's APIText to imageImage editing
Seedream 5.0 Pro
seedream-5.0-pro
ByteDance's Seedream 5.0 Pro through BytePlus ModelArk: one image per task, from text or up to ten of your images. BytePlus's content moderation applies, so explicit requests are refused.
$0.05 per imagePublisher's APIText to imageImage editing