Appearance
Site language
Price currency
DeepSeek via the Evrona gateway

DeepSeek API: get a key, check prices, send a request

Evrona puts DeepSeek models behind an OpenAI-compatible endpoint. Your requests go through the Evrona gateway, so one Evrona key covers DeepSeek along with every other model in the catalog, and everything is billed from a single prepaid balance.

There is no DeepSeek platform account to set up and no foreign card to attach: you top up in rubles with a code and point your existing OpenAI client at Evrona. The current DeepSeek lineup with prices, the sign-up steps and copy-ready curl and Python code are below.

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

DeepSeek models on Evrona and their prices

These are the DeepSeek models currently enabled in the Evrona catalog. Input and output are priced separately per million tokens; pass the Model ID shown under each name as the model parameter.

Model and Model IDTypeInput, per 1M tokensOutput, per 1M tokens
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashConversation$0.03$0.15
DeepSeek V4 Prodeepseek/deepseek-v4-proConversation$0.38$0.84
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813Conversation$0.21$0.78
DeepSeek V4 Flashdeepseek/deepseek-v4-flashConversation$0.03$0.07

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

How to get a DeepSeek 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 DeepSeek models and the rest of the catalog straight away, and you can put a spending cap on it.

DeepSeek 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 deepseek/deepseek-v4.1-flash.

curl

curl
curl https://evrona.ru/v1/chat/completions \
  -H "Authorization: Bearer ev-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash",
    "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="deepseek/deepseek-v4.1-flash",
    messages=[
        {
            "role": "user",
            "content": "Hi! Tell me about yourself in two sentences."
        }
    ],
)
print(completion.choices[0].message.content)

DeepSeek API pricing and payment

Teams usually reach for DeepSeek when a job burns through a lot of tokens — support bots, document processing, writing and reviewing code. A request costs its input plus output tokens at the rates above, with no subscription or minimum spend.

  • 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.

DeepSeek API FAQ

How do I get a DeepSeek API key?

Sign up for Evrona, top up your balance with a code and create a key in the dashboard. The ev-… key works with DeepSeek models and the rest of the catalog at once — there is no separate key per model maker.

Is this the official DeepSeek API?

No. Evrona is an independent gateway: your DeepSeek requests go through Evrona, and the key, balance and pricing are ours. You don't need an account on the DeepSeek platform.

How much does the DeepSeek API cost here?

Evrona's prices for DeepSeek models are in the table on this page and in the catalog, quoted separately for input and output per million tokens. You are charged only for what you use, with no monthly fee. The cost calculator gives a quick estimate for your volume.

How do I pay for it?

From your prepaid Evrona balance. You buy a top-up code in the store with rubles and redeem it in your dashboard; the amount appears on your balance immediately. No foreign card or VPN is required.

Which base URL and Model ID should I use?

Use the Evrona address with the /v1 suffix as the base URL, your Evrona key as the API key, and a Model ID from the table — they all start with deepseek/. Nothing else in your OpenAI SDK code for Python or JavaScript has to change.

Can the same key call other models?

Yes. One Evrona key works with every enabled model in the catalog, including GPT, Claude, Gemini and Qwen. Switching models is just a different Model ID in the request, and they all draw on the same balance.

Start using DeepSeek through Evrona

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