🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

Gemini 3 Pro Image (Preview) Released 2025-11-20

Google image
Input$2/M
Output$120/M
Knowledge cutoff2025-01

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing.

Use Gemini 3 Pro Image (Preview) in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/images/generations

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.images.generate(
    model="gemini-3-pro-image-preview",
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

About Gemini 3 Pro Image (Preview)

Studio-quality visuals up to 4K
Thinking plans complex compositions
Search grounding keeps imagery factually anchored

Gemini 3 Pro Image (preview), marketed as Nano Banana Pro, is Google's reasoning-driven engine for professional-grade image generation and editing, positioned for studio-quality visuals up to 4K with precise text rendering.

  • It targets graphic design, product mockups, and data visualization, using thinking to plan complex compositions and Google Search grounding to keep imagery factually anchored.
  • The model accepts image and text input and returns image and text output, with 65,536 input and 32,768 output tokens.
  • Synthorai delivers it through the same OpenAI-compatible endpoint as its other image models.

Specs & limits

Max output (vendor spec)32,768
Modalitiestext + image → image + text
Featuresvision · structured_output · batch · reasoning
Image capabilitiesProfessional-grade, reasoning-driven image generation and editing (Nano Banana Pro); accurate text rendering; real-world grounding via Google Search; image+text in, image+text out
NotableGateway id has no live official page; current official model code is gemini-3-pro-image; caching and function calling not supported.

per Google official docs ↗

FAQ

Is the Gemini 3 Pro Image (Preview) API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Gemini 3 Pro Image (Preview) against your real workload before adding a payment method.

What is Gemini 3 Pro Image (Preview) best at?

Studio-quality visuals up to 4K, plus thinking plans complex compositions and search grounding keeps imagery factually anchored. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3 Pro Image (Preview) cost?

Gemini 3 Pro Image (Preview) costs $2 per million input tokens and $120 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.

How do I generate images with the Gemini 3 Pro Image (Preview) API?

POST to /v1/images/generations on Synthorai with model="gemini-3-pro-image-preview". It follows the OpenAI images API shape, so no vendor SDK is needed.

How do I get access to Gemini 3 Pro Image (Preview)?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3-pro-image-preview", and you're done. One API key covers every model on the gateway.

Related models

Get your free API key Compare your cost →