Documentation Index Fetch the complete documentation index at: https://developer.pixelbyte.app/docs/llms.txt
Use this file to discover all available pages before exploring further.
Generate high-quality images from text prompts using ByteDance+ Seedream V5 Lite, featuring Chain-of-Thought reasoning and up to 4K output. Supports batch generation of up to 4 images per request.
Property Value Provider ByteDance+ Model Seedream V5 Lite Capability Text to Image Base Cost 35,000 micro-cents/image ($0.035/image) Processing Time ~60 seconds
Request Body
Model slug. Use bytedance-plus/seedream-v5-lite/text-to-image.
Input parameters for text-to-image generation. Text description of the image to generate (max 5000 characters).
Output resolution. Default: 2K. Options: 1K, 2K, 4K.
Output aspect ratio. Default: 1:1. Options: 1:1, 16:9, 9:16, 3:2, 2:3, 4:3, 3:4.
Number of images to generate per request. Default: 1. Options: 1, 2, 3, 4.
HTTPS URL to receive a webhook notification when the job completes or fails.
Pricing
Base cost: 35,000 micro-cents per image ($0.035/image)
finalCost = baseCost × num_images
Factor Option Multiplier Number of Images 11x 22x 33x 44x
Default cost: 1 image = 35,000 × 1 = 35,000 micro-cents ($0.035)
Response
Unique identifier for the submitted job.
Initial job status. Always "pending" on successful submission.
ISO 8601 timestamp of the estimated completion time.
The cost of the job in micro-cents.
Code Examples
curl -X POST https://api.muvi.video/v1/jobs/submit \
-H "Authorization: Bearer $PIXELBYTE_API_KEY " \
-H "Content-Type: application/json" \
-d '{
"model": "bytedance-plus/seedream-v5-lite/text-to-image",
"input": {
"prompt": "An ultra-detailed 4K product shot of a glass perfume bottle on marble"
}
}'