Study and science
Explains formulas and theorems, checks calculations and conclusions, helps with math and physics problems.
> Solve this physics problem and explain the solution> open gemini --ru_
Gemini in Russia without a VPNGemini 4 Argon, 3.8 Flash, 2.5 Pro, and Gemma in the P2D AI aggregator — no subscription
Google models in one account: the flagship Gemini 4 Argon, fast Flash models, and open Gemma models. Write in Russian, and top up your balance via SBP.
- Gemini 4 Argon$0.018
- Gemini 3.8 Flash$0.0074
- Gemini 3.5 Flash Lite$0.0041
- Gemini 3.1 Pro Preview$0.021
FastStudyScienceCode
> you: Explain the Pythagorean theorem using a ladder as an example
gemini-3.8-flash ▸ The ladder, the wall, and the floor form a right triangle. If the bottom of the ladder is 3 m from the wall and the top is at a height of 4 m, then the ladder's length is √(3² + 4²) = 5 m.
[ok] answer ready · charged $0.0074 · $10 gets you ≈ 1,346 such answers
> ls ./gemini
Gemini models in the aggregator
The aggregator has 20 Google text models — Gemini and the open Gemma. The main ones:
- October 2026
Gemini 4 Argonnew
Google's flagship reasoning model: complex development, deep math and science, autonomous tasks.
- context
- 1M
- regular response
- $0.018
- for $10
- ≈ 555
- September 2026
Gemini 3.8 Flash
The smartest model in the Flash line: noticeably stronger than 3.7 Flash in programming and multi-step tasks.
- context
- 1M
- regular response
- $0.0074
- for $10
- ≈ 1,346
- July 2026
Gemini 3.5 Flash Lite
An economical model for simple, high-volume tasks: short answers, translations, processing a large stream of requests.
- context
- 1M
- regular response
- $0.0041
- for $10
- ≈ 2,439
- February 2026
Gemini 3.1 Pro Preview
The previous-generation Pro reasoning model: development and reliable tool use.
- context
- 1M
- regular response
- $0.021
- for $10
- ≈ 480
- June 2025
Gemini 2.5 Pro
The 2025 Pro model for reasoning, code, math, and science — it “thinks” before answering.
- context
- 1M
- regular response
- $0.017
- for $10
- ≈ 606
- April 2026
Gemma 4 31B
An open Google DeepMind model: understands text and images, 256K-token context.
- context
- 262K
- regular response
- free
- for $10
- —
> gemini --help
What Gemini can do
Long materials
Current models accept up to 1M tokens: a book, lectures, or a large project in full.
> Make notes on this book by chapterCode and layout
Writes code, page layouts, and scripts, explains errors, and helps build a small website.
> Build a landing page for a coffee shopQuick answers
Flash Lite responds quickly and costs a fraction of a cent — suited to translations and high-volume tasks.
> Translate 50 product names into English> price gemini --beta 1.0
How much does Gemini cost
No subscription: pay only for responses. The price is from $0.00015 to $0.021 per typical response.
Beta 1.0 prices may change
Response size
≈ a 1000-token request and a 700-token answer — a typical conversation
| Model | Request, $ per 1M tokens | Response, $ per 1M tokens | Context | One response | $10 is enough for | ||||
|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | $4 | $20 | 1M | $0.0072 | $0.018 | $0.072 | ≈ 1,388 | ≈ 555 | ≈ 138 |
| Gemini 3.8 Flash | $1.65 | $8.25 | 1M | $0.003 | $0.0074 | $0.03 | ≈ 3,367 | ≈ 1,346 | ≈ 336 |
| Gemini 3.7 Flash | $1.5 | $7.5 | 1M | $0.0027 | $0.0067 | $0.027 | ≈ 3,703 | ≈ 1,481 | ≈ 370 |
| Gemini 3.6 Flash | $1.5 | $7.5 | 1M | $0.0027 | $0.0067 | $0.027 | ≈ 3,703 | ≈ 1,481 | ≈ 370 |
| Gemini 3.5 Flash Lite | $0.6 | $5 | 1M | $0.0017 | $0.0041 | $0.015 | ≈ 5,952 | ≈ 2,439 | ≈ 675 |
| Gemini 3.5 Flash | $3 | $18 | 1M | $0.0063 | $0.016 | $0.06 | ≈ 1,587 | ≈ 641 | ≈ 166 |
| Gemini 3.1 Flash Lite | $0.5 | $3 | 1M | $0.001 | $0.0026 | $0.01 | ≈ 9,523 | ≈ 3,846 | ≈ 1,000 |
| Gemma 4 26B A4B | 0 | 0 | 262K | free | free | free | without limits | without limits | without limits |
| Gemma 4 31B | 0 | 0 | 262K | free | free | free | without limits | without limits | without limits |
| Gemini 3.1 Flash Lite Preview | $0.5 | $3 | 1M | $0.001 | $0.0026 | $0.01 | ≈ 9,523 | ≈ 3,846 | ≈ 1,000 |
| Gemini 3.1 Pro Preview | $4 | $24 | 1M | $0.0084 | $0.021 | $0.08 | ≈ 1,190 | ≈ 480 | ≈ 125 |
| Gemini 3 Flash Preview | $1 | $6 | 1M | $0.0021 | $0.0052 | $0.02 | ≈ 4,761 | ≈ 1,923 | ≈ 500 |
| Gemini 2.5 Flash Lite | $0.2 | $0.8 | 1M | $0.0003 | $0.00076 | $0.0032 | ≈ 33,333 | ≈ 13,157 | ≈ 3,125 |
| Gemini 2.5 Flash | $0.6 | $5 | 1M | $0.0017 | $0.0041 | $0.015 | ≈ 5,952 | ≈ 2,439 | ≈ 675 |
| Gemini 2.5 Pro | $2.5 | $20 | 1M | $0.0067 | $0.017 | $0.06 | ≈ 1,481 | ≈ 606 | ≈ 166 |
| Gemini 2.5 Pro Preview 06-05 | $2.5 | $20 | 1M | $0.0067 | $0.017 | $0.06 | ≈ 1,481 | ≈ 606 | ≈ 166 |
| Gemma 3 4B | $0.08 | $0.1 | 131K | $0.000054 | $0.00015 | $0.00084 | ≈ 185,185 | ≈ 66,666 | ≈ 11,904 |
| Gemma 3 12B | $0.1 | $0.3 | 131K | $0.00012 | $0.00031 | $0.0014 | ≈ 83,333 | ≈ 32,258 | ≈ 7,142 |
| Gemma 3 27B | $0.16 | $0.7 | 131K | $0.00026 | $0.00065 | $0.0027 | ≈ 38,759 | ≈ 15,384 | ≈ 3,731 |
| Gemma 2 27B | $1.3 | $1.3 | 8K | $0.00078 | $0.0022 | $0.013 | ≈ 12,820 | ≈ 4,524 | ≈ 769 |
The estimate is approximate: the cost of a response depends on the length of your request and the model's answer. The actual generation cost is deducted from your balance.
> cat ./how-to-start.txt
How to use Gemini in Russia
- 01
Sign up for P2D
One account opens all the aggregator's models — no need to register with each one separately.
- 02
Top up your balance via SBP
Balance in dollars. No foreign card or VPN needed, no monthly fee.
- 03
Choose Gemini
Open the AI aggregator, choose a model, and ask your question in Russian. The cost of the result is deducted from your balance.
> man gemini
FAQ about Gemini
How to use Gemini in Russia?
Sign up for P2D, top up your balance via SBP, and choose Gemini in the AI aggregator. No VPN or foreign card needed.
Do you need a VPN for Gemini?
No. The P2D aggregator opens from Russia without a VPN, and the service itself sends the requests to the model.
How much does Gemini cost?
No subscription — you pay for each response. A typical Gemini 4 Argon response costs about $0.018, so $10 covers about 555 such responses. Prices for all models are in the table on this page.
Is there a subscription for Gemini?
No subscription: you top up your balance in dollars and spend it only on what you generate. The same balance works for all of the aggregator's models.
How does Gemini 4 Argon differ from Gemini 3.8 Flash?
Argon is the flagship for the hardest tasks: science, math, development. Flash is faster and cheaper and handles most everyday tasks. A typical Flash response costs about 2.5 times less.
Are there free Gemini models?
The open Gemma 4 models are free in the aggregator. Gemini models are paid, but a Flash Lite response costs a fraction of a cent.
Can Gemini generate images?
For images, Google has separate Nano Banana models — they're also in the aggregator. The Gemini models on this page work with text.
Does Gemini understand Russian?
Yes. Write in Russian — Gemini will answer in Russian and translate into another language if needed.
Other models in the aggregator
> start --gemini
Try Gemini right now
Sign up in a minute, top up via SBP, pay only for the result.