Gemini 3.1 Pro API in Russia — no VPN, no foreign card
Gemini 3.1 Pro is Google's third-generation Pro model for multimodal analysis, agents and coding that need precise tool use. 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-3.1-pro-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)Replace sk-... with a key from the RuAPI Console — the model gemini-3.1-pro-preview is already set.
Gemini 3.1 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-3.1-pro-preview | $2.40 cache read $0.24 >200K: $4.80 | $14.40 >200K: $21.60 |
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.
The grey “>200K” line is the vendor’s official tier for long prompts: when a prompt exceeds the threshold, the whole request is billed at that tier.
What is Gemini 3.1 Pro
Google aims Gemini 3.1 Pro at multimodal understanding, agentic workflows and coding — tasks that need precise tool calls and reliable multi-step execution. The model is still in preview, and Google now presents the newer Gemini 4 Argon as its flagship.
Russia isn't on the list of countries where Google offers the Gemini API, so the model can't be used from Russia directly; through RuAPI you call it via the OpenAI-compatible API or the native Gemini format. Thinking is on by default and its depth is set with thinking_level (low, medium or high), so you can lower it for simple agent steps and get faster answers. The model supports function calling and JSON output that follows a given schema.
Gemini 3.1 Pro specs
| Developer | |
| Model ID in the RuAPI API | gemini-3.1-pro-preview |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens |
| Input | text, images, video, audio, PDF |
| Output | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Prompt caching | yes |
| Status | preview |
| Protocols on RuAPI | OpenAI (/v1/chat/completions) · Gemini (/v1beta) |
Specs are from Google’s official documentation (ai.google.dev), checked Oct 22, 2026.
What it’s good for
- Agents that need precise function calls and reliable step-by-step execution
- Coding: writing, editing and reviewing code
- Analyzing documents, images, video and audio together with text
- Existing integrations whose prompts and flows are already tuned for 3.1 Pro
When another model is a better fit
- Gemini 4 Argon — A newer GA model that Google calls its flagship — for new projects, hard coding tasks and autonomous agents.
- Gemini 3.5 Flash-Lite — Faster and cheaper for high-volume translation, document parsing and data extraction.
Gemini 3.1 Pro: price on RuAPI and elsewhere
| RuAPI | AITUNNEL | ProxyAPI | |
|---|---|---|---|
| Input, $ per 1M tokens | $2.40 | ≈ $4.88 | ≈ $7.319 |
| Output, $ per 1M tokens | $14.40 | ≈ $29.28 | ≈ $44.40 |
AITUNNEL and ProxyAPI prices are from their public pages as of Oct 22, 2026 (ProxyAPI prices include VAT, as on their site), converted at the Bank of Russia rate (81.97 ₽ per $1). The RuAPI price is current.
How to connect Gemini 3.1 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-3.1-pro-preview. 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 3.5 Flash-Lite · Nano Banana Pro