Gemini Nano Banana 2.1 API in Russia — no VPN, no foreign card
Gemini Nano Banana 2.1 is Google's new model for image generation and conversational editing: up to 4K resolution and up to 14 reference images. 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-nano-banana-2.1",
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-nano-banana-2.1 is already set.
Gemini Nano Banana 2.1 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-nano-banana-2.1 | $1.80 | $9.00 ≈ $0.040 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: $36.00 per 1M image output tokens. By Google's figures, a 1K image is about 1,120 tokens (≈ $0.040), a 2K image is about 1,680 tokens (≈ $0.060), a 4K image is about 3,780 tokens (≈ $0.136). The model reasons before drawing; those tokens are billed at the output price in the table.
What is Gemini Nano Banana 2.1
Gemini Nano Banana 2.1 became generally available (GA) on October 6, 2026. Google calls it its latest high-efficiency model for image generation and conversational editing and names it as the replacement for Nano Banana 2 (Gemini 3.1 Flash Image). It accepts text, images, video and PDF and returns images and text; a request can include up to 14 reference images: up to 10 objects and up to 4 characters.
Resolution is 1K (default), 2K or 4K; there is no 0.5K option. Besides the usual aspect ratios, it supports tall and wide formats: 1:4, 4:1, 1:8 and 8:1. Thinking is always on, with minimal, medium (default) and high levels. It doesn't support function calling or JSON-schema output: it's a model for graphics, not for agents.
Gemini Nano Banana 2.1 specs
| Developer | |
| Model ID in the RuAPI API | gemini-nano-banana-2.1 |
| Context window | 131,072 tokens |
| Max output | 32,768 tokens |
| Input | text, images, video, PDF |
| 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
- Illustrations, banners and covers at up to 4K
- Step-by-step image editing in a conversation
- Series of images with the same characters and objects from reference images
- Very tall and very wide formats — up to 1:8 and 8:1
When another model is a better fit
- Nano Banana Pro — Nano Banana Pro: in Google's words, a reasoning-driven model for professional-grade image generation and editing
- GPT Image 2.5 Flare — OpenAI's model for fast everyday generation; edits go through /v1/images/edits
How to connect Gemini Nano Banana 2.1 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-nano-banana-2.1. For the Google GenAI SDK, the address is https://www.ruapi.ai, without /v1beta.
FAQ
See also: Gemini API in Russia · Documentation · Gemini 4 Argon · Gemini 3.1 Pro · Gemini 3.5 Flash-Lite · Nano Banana Pro