Seedream v5.0 Lite API (TokenHub)

ByteDance Seedream v5.0 Lite, a fast and cost-effective tier reachable through the TokenHub gateway — 2K-to-4K output, group images and a built-in web-search tool, billed by real token usage.

~$0.034

Reference / image

2K–4K

Size range

≤14

Reference images

Platform fee

Why use Seedream v5.0 Lite (TokenHub) on NovAI?

Fast & cost-effective - the Lite tier of Seedream v5.0
Up to 4K - high-resolution output
Group images - generate multiple related subjects
Web-search tool - grounded, up-to-date visual concepts
Up to 14 references - the most reference slots of any model here
Token billing - pay only for real upstream token usage

Best use cases

High-volume fast image generation
Group / multi-subject scenes
Web-grounded visual concepts
4K marketing assets on a budget
Rapid design iteration

Quick start

cURL

curl https://aiapi-pro.com/v1/images/generations \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-image-v5.0-lite",
    "prompt": "a group of three friends hiking at sunset, cinematic",
    "size": "2048x2048",
    "n": 1
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.images.generate(
    model="seedream-image-v5.0-lite",
    prompt="a group of three friends hiking at sunset, cinematic",
    size="2048x2048",
    n=1,
)
print(resp.data[0].url)

Billed by real upstream token usage (usage.total_tokens). The ~$0.034 figure is a reference price at base resolution and scales with resolution & reference-image count.