Alice AI API — price in US dollars
Alice AI, the flagship Yandex model: 131K context, requests processed in Russia. Connect it through the kosareva.cloud OpenAI-compatible API; companies outside Russia pay by USD invoice.
What Alice AI is
Alice AI is the flagship Yandex language model, the one Alice answers with. It has a 131K-token context window, takes text in and gives text out, and belongs to the chat and text generation category. Through kosareva.cloud it is available via one OpenAI-compatible API: the same code as for OpenAI — just change base_url and the key.
Alice AI is not available on OpenRouter as of October 2026. Here a company outside Russia gets it with an English invoice in US dollars from Kosareva Cloud LLC (Armenia) and pays by bank transfer. Requests to Alice AI are processed in Russia, on Yandex infrastructure.
One key opens more than Alice AI: the catalog has over a hundred models, including the other Yandex models. That matters more than it seems: models age within months, and moving to the next version is one line of code, not a new contract and a new integration.
Alice AI strengths and weaknesses
Natural Russian: the phrasing reads as written, not translated. Context of 131,072 tokens. Requests are processed in Russia — the argument that settles the question for customers who require processing there.
Expensive: $8.19 per million input tokens and $19.65 per million output, the level of Western flagships, while it does not compete with them on complex reasoning and code. No cache discount at all: repeated context costs as much as new, so a fixed prompt prefix saves nothing. The vendor does not publish the maximum answer length. There is no backup route.
Who it suits. Russian texts where natural language matters: marketing, customer emails, editing. And tasks that require processing in Russia.
What to compare it with. Against Alice AI Flash ($1.64 / $3.27): five times more expensive on input and noticeably smarter. Against YandexGPT 5.1 Pro ($13.10 for both input and output): cheaper on input, more expensive on output, with four times the context.
Alice AI among the Yandex models
Of the Yandex models in our catalog, Alice AI has the largest context: 131K tokens, against 65K for Alice AI Flash and 32K for YandexGPT 5.1 Pro, 5 Pro and 5 Lite. It is the one to pick when the request carries a long document; for a stream of short answers, Flash costs a fifth of the price on input.
Alice AI price in US dollars
| Input | $8.19 per 1M tokens |
| Output | $19.65 per 1M tokens |
Approximate: the catalog price (700 ₽ and 1,680 ₽ per 1M tokens) divided by 85.5 ₽ per $1, ID Bank’s non-cash rate on 3 October 2026. Your balance is kept in rubles; a USD invoice is converted at ID Bank’s non-cash rate on the invoice date. You pay only for actual usage.
What a typical task costs on Alice AI
A price per million tokens says little on its own, so here are four common tasks at Alice AI rates: $8.19 per million input tokens and $19.65 per million output tokens.
| Chat or bot answer1,000 tokens in, 500 out | $0.02 |
| 30-page document review40,000 tokens in, a 2,000-token summary out | $0.37 |
| Article or sales proposal2,000 tokens of brief in, 4,000 out | $0.09 |
| A month of support: 1,000 requests1,500 tokens in and 400 out each | $20.14 |
Calculated from the current kosareva.cloud price list, in US dollars at 85.5 ₽ per $1.
Alice AI cost calculator
Move the sliders to your volume — the monthly cost in US dollars updates at once, with no sign-up.
At $8.19 per million input tokens and $19.65 per million output tokens; approximate, at 85.5 ₽ per $1. Billed for actual usage.
How to connect Alice AI
Use the standard OpenAI SDK with the kosareva.cloud base_url and the model alice-ai. In existing code you change exactly two lines: the address and the key.
Python, OpenAI SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_KOSAREVA_KEY",
base_url="https://api.kosareva.cloud/v1",
)
response = client.chat.completions.create(
model="alice-ai",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Python without the SDK: requests
import requests
response = requests.post(
"https://api.kosareva.cloud/v1/chat/completions",
headers={"Authorization": "Bearer YOUR_KOSAREVA_KEY"},
json={
"model": "alice-ai",
"messages": [{"role": "user", "content": "Hello!"}],
},
timeout=600,
)
print(response.json()["choices"][0]["message"]["content"])cURL
curl https://api.kosareva.cloud/v1/chat/completions \
-H "Authorization: Bearer YOUR_KOSAREVA_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"alice-ai","messages":[{"role":"user","content":"Hello!"}]}'The same key works with any client that supports an OpenAI-compatible endpoint: LangChain, LlamaIndex, Cursor, Continue, n8n. You don’t need a separate key per model — one key opens the whole catalog.
Alice AI endpoints and parameters
The gateway follows the OpenAI schema, so parameter names and the response format are the ones you know. One base address for every model in the catalog.
| base_url | https://api.kosareva.cloud/v1 |
| Endpoint | /chat/completions |
| Model name | alice-ai |
| Authorization | Authorization: Bearer <key> |
| Streaming | stream: true — the answer arrives as it is generated |
| Main parameters | temperature, max_tokens, top_p, stop, tools |
| Model list | GET /v1/models |
Request long answers with stream: true: with a large max_tokens, a regular request stays silent until generation ends and can hit your HTTP client’s timeout. In streaming mode the first tokens arrive within seconds, and the timeout problem goes away.
Specifications
| Provider | Yandex |
| Type | Chat and text generation |
| Context | 131K tokens |
| Input | Text |
| Output | Text |
| API | OpenAI-compatible |
| Processing | In Russia |
What Alice AI is good for
- Chatbots, assistants, Q&A and customer support in Russian
- Copy, newsletters, product descriptions and content marketing in Russian
What to keep in mind with Alice AI
Don’t build a dialogue that keeps growing its history on this model: with no cache discount, every new turn pays again for the whole previous context. Send one compact request with the fragments you need instead of a long conversation — with no cache discount, this is where most of the savings are.
First, context runs out faster than it seems. In a dialogue the whole conversation goes into the input, not just the last message, so a long chat gets more expensive with every turn. If the history isn’t needed for the answer, trim it: savings on input tokens usually matter more than picking a cheaper model.
Second, the 131K-token window is shared between the request and the answer: the more you send, the less room the model has to generate. Set max_tokens on purpose, not “with a margin”.
Third, the balance is shared by all models in the catalog. You don’t have to decide in advance how much money to “put on Alice AI”: the same funds go to any other model if you switch tomorrow. Usage per model is shown in the dashboard on a separate line, with the number of requests and tokens.
Alice AI for companies outside Russia
Alice AI by Yandex, the flagship model: 131K context, requests processed in Russia. Access through kosareva.cloud with an OpenAI-compatible API and a USD invoice for companies.
- Register as “Company or sole proprietor” → “In another country”: country of registration, company registration number, tax ID if you have one.
- In “Top up balance”, “Issue invoice (companies)” gives an English invoice in US dollars from Kosareva Cloud LLC (Armenia): minimum $50, due in 10 days.
- Pay by bank transfer to our USD account at ID Bank. The balance is credited after the bank confirms the payment, usually in 1–3 business days.
- Cards issued outside Russia are not accepted. Invoices are in USD; for EUR, write to us.
- Pay only for actual usage, no subscription. One OpenAI-compatible API for Alice AI and over a hundred other models with one key.
Requests to Alice AI are processed in Russia, on Yandex infrastructure. If you are in the EU or send personal data of EU residents, assess the GDPR side before you send it. You are responsible for compliance with the rules of your jurisdiction.
Other Yandex models
Price per 1M input tokens. The full list with output prices — in the US dollar price table.
Alice AI questions
How much does Alice AI cost?
$8.19 per 1M input tokens and $19.65 per 1M output tokens: 700 ₽ and 1,680 ₽ in the catalog, converted at 85.5 ₽ per $1 (ID Bank’s non-cash rate on 3 October 2026). You pay only for the tokens you use.
How do I connect Alice AI by API?
Register at kosareva.cloud, create a key, set base_url https://api.kosareva.cloud/v1 and the model alice-ai in the standard OpenAI SDK.
What is the context size of Alice AI?
131,072 tokens, shared between the prompt and the answer.
Who is Alice AI for, and where is it weaker?
Russian texts where natural language matters: marketing, customer emails, editing, and tasks that require processing in Russia. It is expensive for its class, does not compete with Western flagships on complex reasoning and code, and gives no cache discount.
Which models should I compare Alice AI with?
With Alice AI Flash ($1.64 / $3.27): Alice AI is five times more expensive on input and noticeably smarter. With YandexGPT 5.1 Pro ($13.10 for input and output): Alice AI is cheaper on input, more expensive on output and has four times the context.
Where are requests to Alice AI processed?
In Russia, on Yandex infrastructure. If GDPR applies to you, assess the transfer before sending personal data. You are responsible for compliance with the rules of your jurisdiction.
How does a company outside Russia pay?
Register as “Company or sole proprietor” → “In another country”, then click “Issue invoice (companies)” in “Top up balance”. You get an English invoice in US dollars from Kosareva Cloud LLC (Armenia), minimum $50, due in 10 days. The balance is credited after the bank confirms the payment, usually in 1–3 business days. Cards issued outside Russia are not accepted.
Can I try Alice AI on a small amount?
The minimum invoice is $50. Usage is billed per token with no subscription, and the unused balance does not expire.
Connect Alice AI in a couple of minutes
Get an API key and call Alice AI through an OpenAI-compatible endpoint. Companies outside Russia pay by USD invoice. Questions: ceo@kosareva.cloud or @kosareva_cloud in Telegram.