WAND Vega Image Flash API

Tencent WAND Vega Image Flash is the balanced mid tier of the Vega image family — strong quality and speed for production workloads, 1K-to-4K output and up to 6 reference images, billed by real token usage.

from ~$0.069

Reference / image

1K–4K

Size range

0–6

Reference images

Platform fee

Why use WAND Vega Image Flash on NovAI?

Balanced mid tier - best quality-to-cost ratio for production
Up to 4K - high-resolution output
Up to 6 references - rich multi-image conditioning
Auto-polled - NovAI waits for the async task and returns the URL
Production ready - consistent quality at scale
Token billing - pay only for real upstream token usage

Best use cases

Production marketing imagery
Multi-reference product shots
Editorial and blog illustrations
Ad creative at scale
Design systems and templates

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-flash",
    "prompt": "a futuristic city skyline at night, neon lights",
    "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-flash",
    prompt="a futuristic city skyline at night, neon lights",
    size="1024x1024",
    n=1,
)
print(resp.data[0].url)

Billed by real upstream token usage (usage.total_tokens). The from ~$0.069 figure is a reference price at base resolution and scales with resolution & reference-image count.