Hunyuan Image 3.0 API

Tencent's flagship Hunyuan Image 3.0 text-to-image model, accessible through NovAI's OpenAI-compatible /v1/images/generations endpoint — synchronous response, built-in prompt rewrite and custom watermark, at real token cost with zero platform fee.

~$0.031

Reference / image

1024²

Max size

0–3

Reference images

Platform fee

Why use Hunyuan Image 3.0 on NovAI?

Flagship quality - Tencent Hunyuan Image 3.0 text-to-image model
Synchronous - single request returns the final image URL, no polling
Prompt rewrite - upstream auto-enhances short prompts
Custom watermark & footnote - control branding and captions
Reference images - up to 3 for image-to-image editing
Token billing - pay only for real upstream token usage

Best use cases

Marketing and social-media visuals
Product mockups and concept art
Illustrations and cover images
Image editing with reference photos
High-volume content pipelines

Quick start

cURL

curl https://aiapi-pro.com/v1/images/generations \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy-image-v3",
    "prompt": "a cute orange cat on a windowsill, soft sunlight",
    "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="hy-image-v3",
    prompt="a cute orange cat on a windowsill, soft sunlight",
    size="1024x1024",
    n=1,
)
print(resp.data[0].url)

Billed by real upstream token usage (usage.total_tokens). The ~$0.031 figure is a reference price at base resolution and scales with resolution & reference-image count.