Flowise in Russia: Claude, GPT, DeepSeek and Qwen for chatbots and agents without a VPN
Flowise is an open-source Node.js builder for AI agents, chatbots and RAG: you assemble flows from nodes with the mouse, then embed the bot on a website or call it via API. Flowise has no models of its own. Give the OpenAI Custom Model node the Base Path https://www.ruapi.ai/v1 and a RuAPI key, and Claude, GPT, Gemini, DeepSeek and Qwen start working. No VPN, pay in USDT.
# Chat Models node → OpenAI Custom Model
Connect Credential: OpenAI API credential (your RuAPI key)
Model Name: deepseek-flash
# Additional Parameters
Base Path: https://www.ruapi.ai/v1The Chat Model tab shows the OpenAI Custom Model node settings, Embeddings the OpenAI Custom Embedding node. Base Path is under Additional Parameters and must end in /v1. The Terminal tab installs via npm (Node.js 24 needed); Docker works too.
What gets in the way of connecting models to Flowise from Russia
Without a model key Flowise nodes do nothing.
Every chatbot and agent in Flowise calls the model through a provider node, and it needs a key. Anthropic and OpenAI do not offer their APIs in Russia: it is missing from their supported-country lists (anthropic.com/supported-countries, developers.openai.com, checked 10 Nov 2026). A RuAPI key is issued right after you sign up with email, Google, Yandex or Telegram.
Not every node accepts your own address and model name.
The OpenAI node only lets you pick a model from a built-in list, and the Anthropic Claude node has no API address field. So for RuAPI use OpenAI Custom Model: you type the model name and set the address in Base Path. Claude, GPT and DeepSeek all work through this node.
The Flowise server is often in Russia.
Flowise is installed on your own server, and model requests go straight from it. Keeping a VPN on a server is awkward and unreliable. www.ruapi.ai is reachable from Russia directly, and every model works with one key and one balance.
How to connect: 3 steps
Works for Flowise installed via npm or Docker.
Sign up for RuAPI and top up
Sign up at www.ruapi.ai with email, Google, Yandex or Telegram. The minimum top-up is 5 USDT on TRC20, BEP20, TON or Polygon; USDC is accepted too. How to buy USDT for rubles via SBP is shown at docs.ruapi.ai/en/buy-usdt. Foreign bank cards also work.
A new account usually gets $0.05 right away for deepseek-flash, claude-haiku-5-5 and gpt-6-luna — enough to test your first chat flow. Embeddings (document search) unlock after your first top-up.
Create a key and save it in Flowise
Console → “API keys” → “Create key”. In Flowise open Credentials → Add Credential → OpenAI API and paste the RuAPI key into OpenAI Api Key. It is a regular OpenAI credential — Flowise does not care that the key is from another service; the address is set in the node itself.
Add nodes with the RuAPI address
- Chat Models → OpenAI Custom Model: pick the saved key in Connect Credential and type a model in Model Name, for example deepseek-flash or claude-sonnet-5-5.
- Open Additional Parameters and set Base Path to https://www.ruapi.ai/v1 — with /v1 at the end, or the request goes to the wrong address. Streaming is switched on there too.
- For RAG: Embeddings → OpenAI Custom Embedding with the same credential, Model Name text-embedding-3-small, Base Path https://www.ruapi.ai/v1.
- If a node does not answer, check the model name: it must match the name on the RuAPI pricing page exactly.
RuAPI addresses and keys: docs.ruapi.ai/en/quickstart · tool calling: docs.ruapi.ai/en/function-calling
What to enter in Flowise
OpenAI Custom Model
Base Path: https://www.ruapi.ai/v1
Model Name: deepseek-flash, claude-sonnet-5-5…
OpenAI API credential
OpenAI Api Key: sk-…
one credential for chat and embeddings
Embeddings
OpenAI Custom Embedding
text-embedding-3-small — $0.024 per 1M tokens
Prices of models for Flowise
In US dollars per 1M tokens, as on the pricing page. No subscription: only the tokens your requests use are deducted.
| model | input $/M | output $/M |
|---|---|---|
| claude-sonnet-5-5 | $2.40 cache read $0.12 | $12.00 |
| claude-haiku-5-5 | $0.12 cache read $0.0120 >100K: $0.60 | $0.60 >100K: $3.00 |
| gpt-6.1-sol | $2.40 cache read $0.12 >272K: $4.80 | $12.00 >272K: $18.00 |
| gpt-6-luna | $0.12 cache read $0.0120 >272K: $0.24 | $0.60 >272K: $0.90 |
| gemini-4-argon | $2.40 cache read $0.12 | $12.00 |
| deepseek-v4-pro | $1.58 cache read $0.0600 | $4.75 |
| deepseek-flash | $0.17 cache read $0.0120 | $1.44 |
| qwen3.8-flash | $0.14 cache read $0.0288 | $0.49 |
Input is the price of new input tokens (prompt, history, retrieved document chunks), output of the model’s reply. By our estimate, a chatbot message with 5K tokens in and a 500-token reply costs about $0.002 on deepseek-flash and about $0.018 on claude-sonnet-5-5. Indexing 500K tokens of documents with text-embedding-3-small costs about $0.012. Your account’s prices may be lower.
The grey “>100K” row is the vendor’s long-prompt rate: if the prompt is over the threshold, the whole request is billed at it.