n8n in Russia: AI nodes with GPT, Claude and Gemini, no VPN
n8n AI nodes work with any OpenAI-compatible API once you set your own Base URL in the OpenAI credential. Evrona is such an API: one key opens GPT, Claude, Gemini, DeepSeek and the other models in the catalog.
The gateway is reachable from Russia without a VPN, so workflows on your own n8n server reach the models with no workarounds. The prepaid balance is topped up in rubles with a top-up code, and each call is charged by the tokens it actually used.
n8n gets by with a single credential: the OpenAI credential has a Base URL field, and the gateway address goes exactly there.
What to prepare
No key yet? Create an account — keys are created in the dashboard under “API keys”, and the full value is shown only once. Copy the Model ID from the catalog in full, including the prefix before “/”.
Connection steps
Open Credentials → New → OpenAI.
Base URL takes the gateway address ending in /v1, API Key takes your Evrona key.
In the AI node select this credential and enter the Model ID in full.
The AI Agent node works as well: it rests on function calling.
Base URL: https://evrona.ru/v1
API Key: ev-YOUR_KEY
Model: google/gemini-3.7-flashWhen the node answers 404, check the address: most often it is /v1/v1, because the path was typed in by hand.
Function calling is supported, so agentic modes work. Strict JSON mode (response_format) and the retired functions format are turned down with an unsupported_parameter error — no parameter is lost in silence. Image input is taken by models marked "Understands images" in the catalog: a content part of type image_url with a data:image/png;base64,… URL (PNG, JPEG or WebP, up to 5 MB each, up to 50 per request). Remote URLs are not fetched, and a model without that mark returns unsupported_capability — both errors name the reason outright.
Models for n8n
Enter the full Model ID from a card in the AI node.
- GPT-6 Astraopenai/gpt-6-astrainput $0.67 · output $2.22 per 1M
- GPT-5.6 Solopenai/gpt-5.6-solinput $0.67 · output $3.94 per 1M
- GPT-5.6 Terraopenai/gpt-5.6-terrainput $0.29 · output $1.98 per 1M
- GPT-5.6 Lunaopenai/gpt-5.6-lunainput $0.14 · output $0.88 per 1M
- GPT-5.5openai/gpt-5.5input $0.64 · output $3.46 per 1M
- GPT-5.4openai/gpt-5.4input $0.28 · output $1.97 per 1M
n8n FAQ
Do n8n AI nodes need a VPN?
No. n8n talks to the Evrona gateway, and it is reachable from Russia without a VPN — including from self-hosted n8n on a server in Russia.
How do I pay for AI calls from n8n in rubles?
Top up your Evrona balance in rubles with a top-up code: buy the code in the store and redeem it in the dashboard. Every call from a workflow is charged to that balance at catalog prices.
Which n8n nodes work with Evrona?
Nodes that use the OpenAI credential, including AI Agent. The agent needs a model that supports function calling.
Why does the node return 404?
Most often the address ends up as /v1/v1 because the path was typed in by hand. The Base URL field needs the gateway address with a single /v1 at the end, as in the example above.
How do I keep workflow costs under control?
Every request cost shows up in your dashboard history. Give your workflows a separate key with a spending limit per day, week or month.
Get a key for n8n
Signing up takes a couple of minutes. Top up in rubles, create a key in the dashboard and paste it into the n8n OpenAI credential.