Russian without an accent
Alice AI writes natural Russian, without the stiff phrasing of translated output: customer emails, marketing, editing.
YandexGPT and Alice AI by API, paid in US dollars
Alice AI and YandexGPT through an OpenAI-compatible API, with the same key as the rest of our catalog. Requests are processed in Russia; companies abroad pay by USD invoice from $50.
In short: Yandex models are not on OpenRouter as of October 2026. Through kosareva.cloud you connect the Yandex language models — Alice AI, YandexGPT and embeddings — with one key: only base_url and the key change, your OpenAI SDK code stays the same. Requests are processed in Russia. A company outside Russia pays by USD invoice from Kosareva Cloud LLC (Armenia), minimum $50.
Invoice in US dollars
Bank transfer to ID Bank, Armenia
OpenAI-compatible API
Works with any OpenAI SDK
Pay as you go
No subscription, billed per token
Seller named openly
Kosareva Cloud LLC, Armenia
/ Why Yandex
Where Yandex models fit
Not a replacement for Western flagships in code and complex reasoning, but a precise choice for Russian text and for tasks that require processing in Russia.
Processed in Russia
Requests to Yandex models are processed in Russia. A key marked “Russia-hosted models only” cannot reach a model hosted elsewhere, even by mistake.
One price for input and output
YandexGPT 5.1 Pro costs $13.10 per million tokens for both input and output: a long answer costs no more than a long prompt.
Cache discount on Alice AI Flash
A repeated prompt prefix on Flash is billed at $0.41 per million tokens instead of $1.64. The other Yandex models have no cache discount.
Where Yandex is weaker
YandexGPT context is 32,768 tokens, Alice AI’s is 131,072. A whole long contract, code and agents are better served by other models in the catalog — with the same key.
RAG and semantic search
The Yandex Embeddings pair costs $0.17 per million tokens, chunks up to 8,192 tokens: documents go to Doc, queries to Query.
/ Catalog
Yandex models in the catalog
Approximate prices in US dollars per 1M tokens: the catalog price in rubles divided by 85.5 ₽ per $1, ID Bank’s non-cash rate on 3 October 2026. Your balance is kept in rubles.
Yandex131K context
Alice AI
Yandex’s flagship: 131K context, natural Russian, processed in Russia.
$8.19 in · $19.65 out, per 1M tokens
Yandex66K context
Alice AI Flash
The fast Alice AI: five times cheaper on input, with a cache discount and a 65,536-token context.
$1.64 in · $3.27 out, per 1M tokens
Yandex33K context
YandexGPT 5.1 Pro
Current YandexGPT generation: one price for input and output, processed in Russia.
$13.10 in · $13.10 out, per 1M tokens
Yandex33K context
YandexGPT 5 Lite
The smaller YandexGPT: four times cheaper than 5.1 Pro, with the same context.
$3.27 in · $3.27 out, per 1M tokens
Yandex33K context
YandexGPT 5 Pro
Previous YandexGPT Pro generation, kept for integrations already tuned to it.
$19.65 in · $19.65 out, per 1M tokens
Yandexembeddings
Yandex Embeddings Doc
Turns documents into vectors for semantic search: knowledge base, RAG, deduplication.
$0.17 per 1M tokens
/ Setup
First request to Alice AI
OpenAI-compatible endpoint: only base_url and the model name change, the code stays the same.
- /1
Register the company
Choose “Company or sole proprietor” → “In another country”: country, registration number, tax ID if you have one.
- /2
Top up by USD invoice
“Top up balance” → “Issue invoice (companies)”: an English invoice in US dollars, minimum $50, due in 10 days.
- /3
Send the first request
Create a key and set the model: alice-ai, alice-ai-flash, yandexgpt-5-1-pro or yandexgpt-5-lite. Usage shows up in the dashboard right away.
from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.kosareva.cloud/v1", ) response = client.chat.completions.create( model="alice-ai", messages=[{"role": "user", "content": "Translate into Russian: Your order has shipped."}], ) print(response.choices[0].message.content)
import OpenAI from "openai"; const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.kosareva.cloud/v1", }); const response = await client.chat.completions.create({ model: "alice-ai", messages: [{ role: "user", content: "Translate into Russian: Your order has shipped." }], }); console.log(response.choices[0].message.content);
curl https://api.kosareva.cloud/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "alice-ai", "messages": [{"role": "user", "content": "Translate into Russian: Your order has shipped."}] }'
/ Cost
What a month costs
Two typical workloads over 30 days, at the dollar prices above. Chatbot: 500 requests a day, 800 tokens in and 300 out. Documents: 100 requests a day, 20,000 tokens in and 800 out.
| Model | Chatbot, per month | Documents, per month |
|---|---|---|
| Alice AI | $186.67 | $538.39 |
| Alice AI Flash | $34.39 | $106.11 |
| YandexGPT 5.1 Pro | $216.14 | $817.40 |
| YandexGPT 5 Lite | $54.04 | $204.35 |
Approximate, at 85.5 ₽ per $1 (ID Bank, 3 October 2026). The balance is debited in rubles for actual tokens; there is no subscription.
/ Before you start
Payment and data
USD invoice from Armenia
Kosareva Cloud LLC issues the invoice in English and in US dollars to our USD account at ID Bank. The balance is credited after the bank confirms the payment, usually in 1–3 business days.
No foreign cards, no EUR yet
Cards issued outside Russia are not accepted. Invoices are in USD; for EUR, write to us and we’ll discuss it.
Data is processed in Russia
Requests to Yandex models are processed in Russia, on Yandex infrastructure. If GDPR applies to you, assess it before you send personal data.
Your jurisdiction, your rules
You are responsible for compliance with the rules of your jurisdiction. We describe how the service works; we don’t give legal advice.
/ FAQ
Questions
The key, the data and choosing a model.
Where do I get an API key for YandexGPT and Alice AI?
At kosareva.cloud the key is issued in the dashboard right after registration and works with the Yandex models and the rest of the catalog. Yandex models are not on OpenRouter as of October 2026.
Is this the same Alice as in the smart speaker?
The API gives you Alice AI, the language model Alice answers with. There is no voice, skills or smart home in the API: text in, text out — for your own chats, bots and document processing.
Which model should I choose?
Alice AI — for texts where natural Russian matters. Alice AI Flash — for a stream of short answers: five times cheaper on input, and the only Yandex model with a cache discount. YandexGPT 5.1 Pro — when answers are long: input and output cost the same, $13.10 per million. YandexGPT 5 Lite — for labelling and classification at volume.
Does data leave Russia?
Requests to Yandex models are processed in Russia, on Yandex infrastructure. To make sure a key can’t reach a model hosted elsewhere, mark it “Russia-hosted models only” when you create it. If GDPR applies to you, assess the transfer before sending personal data.
How does a company outside Russia pay?
By bank transfer against a USD invoice from Kosareva Cloud LLC (Armenia): minimum $50, due in 10 days. Your balance is kept in rubles; the invoice is converted at ID Bank’s non-cash rate on the invoice date. Cards issued outside Russia are not accepted.
Do you invoice in euros?
Not yet. If you need a EUR invoice, write to ceo@kosareva.cloud or Telegram @kosareva_cloud.
/ Next
Related pages
Test it on your own text
Create a key, send a dozen real requests to Alice AI and YandexGPT and compare the answers with the model you use now.