Appearance
Site language
Price currency
Gemini via the Evrona gateway

Gemini API through one OpenAI-compatible key

Evrona lets you call Gemini models with the same request format you already use for OpenAI. Traffic goes through the Evrona gateway, so a single Evrona key reaches Gemini and every other model in the catalog, all billed from one prepaid balance.

You skip the Google AI Studio or Cloud project setup: create an account, top up in rubles with a code and swap the Model ID. Below you'll find the Gemini models Evrona currently serves, from Pro down to Flash Lite, with their prices, followed by key setup and sample code.

You reach Gemini models through the Evrona gateway. This is not an official Gemini page: Evrona is an independent OpenAI-compatible gateway with its own key, balance and pricing.

Gemini models on Evrona and their prices

This table is built from the live Evrona catalog. Text models are priced per million input and output tokens; the Model ID under each name starts with google/ and goes into the model field of your request.

Model and Model IDTypeInput, per 1M tokensOutput, per 1M tokens
Gemini 4 Argongoogle/gemini-4-argonConversation$0.51$2.10
Gemini 3.8 Flashgoogle/gemini-3.8-flashConversation$0.08$0.34
Gemini 3.7 Flashgoogle/gemini-3.7-flashConversation$0.97$2.17
Gemini 3.6 Flashgoogle/gemini-3.6-flashConversation$0.24$1.49
Gemini 3.1 Progoogle/gemini-3.1-pro-previewConversation$0.94$2.89
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-liteConversation$0.06$0.49
Gemini 3 Flashgoogle/gemini-3-flash-previewConversation$0.16$0.59
Gemini 2.5 Progoogle/gemini-2.5-proConversation$0.78$2.98
Gemini 3.1 Flash Imagegoogle/gemini-3.1-flash-image-previewPicture$0.01 per unit

Accounting inside the service is in USD; EUR prices are recalculated at the current rate and may change.

How to get a Gemini API key

  1. Sign up

    Create an Evrona account with your email — it takes about a minute.

  2. Top up with a code

    Buy a top-up code in the store and redeem it in your dashboard. The amount lands on your prepaid balance right away.

  3. Create a key

    Create an ev-… API key in your dashboard. It works with Gemini models and the rest of the catalog straight away, and you can put a spending cap on it.

Gemini API request example

The gateway speaks the OpenAI API: set the base URL to https://evrona.ru/v1, use your Evrona key and pick a Model ID from the table. The example uses google/gemini-4-argon.

curl

curl
curl https://evrona.ru/v1/chat/completions \
  -H "Authorization: Bearer ev-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-4-argon",
    "messages": [
      {
        "role": "user",
        "content": "Hi! Tell me about yourself in two sentences."
      }
    ]
  }'

OpenAI SDK: Python and JavaScript

from openai import OpenAI

client = OpenAI(
    base_url="https://evrona.ru/v1",
    api_key="ev-YOUR_KEY",
)

completion = client.chat.completions.create(
    model="google/gemini-4-argon",
    messages=[
        {
            "role": "user",
            "content": "Hi! Tell me about yourself in two sentences."
        }
    ],
)
print(completion.choices[0].message.content)

Gemini API pricing and payment

The lighter Flash models are the usual pick for high-volume, latency-sensitive work such as classification, extraction and short chatbot replies, while Pro models are chosen for long documents and multi-step reasoning. Every request is billed on actual usage at the rates listed.

  • Prepaid balance: top up first, then send requests — no subscription and no monthly fee.
  • You top up in rubles with a top-up code that you redeem in your dashboard.
  • You pay only for actual usage at the rates in the table, and every request shows up in your history.

To see what your workload would cost, try the cost calculator.

Gemini API FAQ

How do I get a Gemini API key?

Create an Evrona account, redeem a top-up code and generate a key in your dashboard. That ev-… key accepts google/gemini-… Model IDs and the rest of the catalog, so you don't need a separate Google key.

Do I need a Google AI Studio or Google Cloud account?

No. Gemini requests go through the Evrona gateway and authenticate with your Evrona key. This isn't Google's official Gemini API — the key, balance and prices belong to Evrona.

Which Gemini models can I use?

The ones listed in the table above: Evrona currently offers Gemini models from the Pro and Flash lines, including lighter variants. The lineup follows the catalog, so the table is always the up-to-date list.

What does Gemini API access cost?

Each model's rate is in the table — for text models, separately for input and output per million tokens. You pay only for actual usage at those rates, with no plan or monthly minimum; the cost calculator helps you size a budget.

How do I pay?

Top up your prepaid Evrona balance with a code bought for rubles and redeemed in the dashboard. Gemini usage, like any other model's, is deducted from that balance.

Do I have to rewrite my code for a Gemini SDK?

No. The gateway speaks the OpenAI Chat Completions format: keep the OpenAI SDK or curl, set the base URL to Evrona's /v1 and use a Gemini Model ID from the table.

Start using Gemini through Evrona

Sign up, top up with a code and send your first Gemini request in a few minutes. The same key opens every other model in the catalog.