WAND Vega Image Lite API

Tencent WAND Vega Image Lite is the fast, cost-effective entry tier of the Vega image family — 1K-to-4K generation with up to 3 reference images, exposed through NovAI's OpenAI-compatible endpoint and billed by real token usage.

from ~$0.025

Reference / image

1K–4K

Size range

0–3

Reference images

Platform fee

Why use WAND Vega Image Lite on NovAI?

Entry tier - lowest cost in the WAND Vega family
Up to 4K - high-resolution output even at Lite pricing
Fast generation - optimized for throughput
Auto-polled - NovAI waits for the async task and returns the URL
Up to 3 references - image-to-image editing support
Token billing - pay only for real upstream token usage

Best use cases

High-volume low-cost image generation
Thumbnails and social visuals
Rapid prototyping
Batch content pipelines
Simple image editing tasks

Quick start

cURL

curl https://aiapi-pro.com/v1/images/generations \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wand-vega-image-lite",
    "prompt": "a serene mountain lake at dawn, reflective water",
    "size": "1024x1024",
    "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="wand-vega-image-lite",
    prompt="a serene mountain lake at dawn, reflective water",
    size="1024x1024",
    n=1,
)
print(resp.data[0].url)

Billed by real upstream token usage (usage.total_tokens). The from ~$0.025 figure is a reference price at base resolution and scales with resolution & reference-image count.