gemini-3-pro-image — API, Pricing & Image Tokens | Vivgrid

gemini-3-pro-image, also known as Nano Banana Pro, is Google's highest-quality image generation and editing model. It applies Gemini 3 reasoning to image work, which makes it the strongest option for complex, multi-turn generation and editing, accurate text rendering inside images, and high-fidelity design output.

On Vivgrid, gemini-3-pro-image runs as a globally centralized model reachable through the same OpenAI-compatible endpoint and unified key as every other model in the catalog.

Specifications

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

Image token conversion

Images are billed as tokens, so the per-image cost follows the resolution you ask for:

Text and thinking tokens are billed at the text output rate of $12.00 per 1M tokens.

API surfaces

gemini-3-pro-image is served on /images/generations, behind the same API key as the rest of the catalog.

Quick start

Get an API key from the Vivgrid Console, then call gemini-3-pro-image directly.

curl https://api.vivgrid.com/v1/images/generations \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image",
    "prompt": "A cozy reading nook with plants and warm light",
    "size": "1024x1024"
  }'

Ideal use cases

• Complex graphic design and marketing assets
• High-fidelity product mockups
• Infographics and data visualizations that require accurate text rendering
• Multi-turn, conversational image editing

Related models

• gpt-6-astra — OpenAI's frontier gpt-6 coding model
• gemini-nano-banana-2.1 — the high-volume, lower-cost image model
• gemini-3.5-flash — multimodal understanding rather than generation