Nano Banana Pro API in Russia — no VPN, no foreign card
Nano Banana Pro (gemini-3-pro-image) is Google's reasoning-driven model for professional-grade image generation and editing, billed per token as with Google. Connect through RuAPI: pay in USDT from $5, no subscription, your key right after sign-up.
from openai import OpenAI
client = OpenAI(
api_key="sk-...",
base_url="https://www.ruapi.ai/v1",
)
resp = client.chat.completions.create(
model="gemini-3-pro-image",
messages=[{"role": "user", "content": "Draw a ginger cat in a spacesuit with Saturn in the background"}],
)
print(resp.choices[0].message.content)Replace sk-... with a key from the RuAPI Console — the model gemini-3-pro-image is already set.
Nano Banana Pro API price
Current price in US dollars — the same as on the pricing page. Pay in USDT, pay as you go, no subscription.
| model | input $ / 1M | output $ / 1M |
|---|---|---|
| gemini-3-pro-image | $2.40 | $14.40 ≈ $0.161 per 1K image |
Input is the regular price of input tokens, “cache read” is the price of input tokens served from the prompt cache, output is the price of output tokens. The price in your account may be lower.
Images are billed per token: $144.00 per 1M image output tokens. By Google's figures, a 1K image is about 1,120 tokens (≈ $0.161), a 2K image is about 1,120 tokens (≈ $0.161), a 4K image is about 2,000 tokens (≈ $0.288). The model reasons before drawing; those tokens are billed at the output price in the table.
What is Nano Banana Pro
Gemini 3 Pro Image, also known as Nano Banana Pro, became generally available (GA) on May 28, 2026. Google describes it as a reasoning-driven model for professional-grade image generation and editing: it thinks about the request before producing an image, and this can't be turned off. It takes text and images as input and returns images and text; resolution is 1K (default), 2K or 4K.
On RuAPI you can call it as gemini-3-pro-image or by the short name nano-banana-pro — it's the same model at the same price. Billing is per token, as with Google: input, text output together with thinking, and image output are counted separately. The old ID gemini-3-pro-image-preview still works too, but it has a flat price per request. The model doesn't support function calling or JSON-schema output.
Nano Banana Pro specs
| Developer | |
| Model ID in the RuAPI API | gemini-3-pro-image |
| Context window | 65,536 tokens |
| Max output | 32,768 tokens |
| Input | text, images |
| Output | images, text |
| Reasoning mode | yes |
| Tool calling | no |
| Status | generally available |
| Protocols on RuAPI | OpenAI (/v1/chat/completions) · Gemini (/v1beta) |
Specs are from Google’s official documentation (ai.google.dev), checked Oct 23, 2026.
What it’s good for
- Product mockups and marketplace product cards
- Infographics, diagrams and posters
- Precise edits to existing images from a text description
- Final images in 2K and 4K
When another model is a better fit
- Gemini Nano Banana 2.1 — Google's new model for generation and conversational editing; accepts video, PDF and up to 14 reference images
- Nano Banana Pro Preview — Nano Banana Pro under the old ID with a flat price per request — if you want to know the cost of each image in advance
How to connect Nano Banana Pro from Russia
- Sign up at ruapi.ai — with email, Google or Yandex. No VPN needed.
- Top up with USDT or USDC from 5 USDT. No USDT yet? Buy it with rubles via SBP — step by step in the docs.
- In the Console, open API Keys → Create key.
- Use the address https://www.ruapi.ai/v1 and the model gemini-3-pro-image. For the Google GenAI SDK, the address is https://www.ruapi.ai, without /v1beta.