kosareva.cloud

GigaChat 2 Max API — price in US dollars

Sber · Chat and text generation

GigaChat 2 Max, the previous GigaChat generation: a 131K context, kept for integrations already tuned to it. Connect it through the kosareva.cloud OpenAI-compatible API; companies outside Russia pay by USD invoice.

Modalities
→Input: text. Output: text.
Input / output per 1M
$9.32 / $9.32
Context
131K tokens
Provider
Sber

What GigaChat 2 Max is

GigaChat 2 Max is the previous generation of Sber’s GigaChat family. It has a 131,072-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.

GigaChat is not on OpenRouter as of October 2026, and a direct contract for the GigaChat API needs a Russian company or sole proprietor. Here a company outside Russia gets GigaChat 2 Max with an English invoice in US dollars from Kosareva Cloud LLC (Armenia) and pays by bank transfer. Requests to GigaChat 2 Max are processed in Russia.

One key opens more than GigaChat 2 Max: the catalog has over a hundred models, including the other GigaChat and 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.

GigaChat 2 Max strengths and weaknesses

Where it is good

The previous generation of the family, already built into some working integrations. If your prompts are tuned to it and there is no time to rewrite them, it is available and answers the way it did. Its one measurable advantage over the other GigaChat models: almost no service overhead — 11 tokens per request against 990 on Lightning and 1,214 on 3 Pro.

Where it falls short

Honestly: for new development there is no reason to take it. It is six times more expensive than GigaChat 3.5 Ultra on input and twice on output, has half the context — 131,072 against 262,144 — and, unlike the other three GigaChat models, has no tool calling declared in the vendor’s catalog. This is a compatibility option, not a choice. No backup route; the maximum answer length is not published.

Who it suits. One use: keeping an existing integration running until it moves to the third generation.

What to compare it with. Against GigaChat 3.5 Ultra ($1.58 / $4.73) it loses on price, context and features at once. The absence of service overhead does not make up the difference: $9.32 against $1.58 per million — Ultra’s extra 55 or so tokens don’t weigh that much at any request size.

GigaChat 2 Max among the GigaChat models

GigaChat 2 Max is the oldest and most expensive model of the family. GigaChat 3.5 Ultra has twice the context at a sixth of the input price, GigaChat 3 Pro and GigaChat 3 Lightning are cheaper still. Moving usually means changing the model name and rerunning your tests.

GigaChat 2 Max price in US dollars

Input$9.32 per 1M tokens
Output$9.32 per 1M tokens

Approximate: the catalog price (797.07 ₽ per 1M tokens for both input and output) 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. The vendor’s service prompt, about 11 tokens per request, is billed as input. You pay only for actual usage.

What a typical task costs on GigaChat 2 Max

A price per million tokens says little on its own, so here are four common tasks at GigaChat 2 Max rates: $9.32 per million input tokens and $9.32 per million output tokens, plus the vendor’s service prompt of about 11 input tokens on every request.

Chat or bot answer1,000 tokens in, 500 out$0.01
30-page document review40,000 tokens in, a 2,000-token summary out$0.39
Article or sales proposal2,000 tokens of brief in, 4,000 out$0.06
A month of support: 1,000 requests1,500 tokens in and 400 out each$17.82

Calculated from the current kosareva.cloud price list, in US dollars at 85.5 ₽ per $1, with the service prompt included.

GigaChat 2 Max cost calculator

Move the sliders to your volume — the monthly cost in US dollars updates at once, with no sign-up.

Requests per month
0100,000
Input tokens
060,000
Output tokens
032,000
Input
—
Output
—
Per request
—
Tokens per month
—
Monthly cost
—
Get an API key

At $9.32 per million input tokens and $9.32 per million output tokens; approximate, at 85.5 ₽ per $1. Each request also carries the vendor’s service prompt of about 11 input tokens — it is already in the numbers. Billed for actual usage.

How to connect GigaChat 2 Max

Use the standard OpenAI SDK with the kosareva.cloud base_url and the model gigachat-2-max. 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="gigachat-2-max",
    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": "gigachat-2-max",
        "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":"gigachat-2-max","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.

GigaChat 2 Max 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_urlhttps://api.kosareva.cloud/v1
Endpoint/chat/completions
Model namegigachat-2-max
AuthorizationAuthorization: Bearer <key>
Streamingstream: true — the answer arrives as it is generated
Main parameterstemperature, max_tokens, top_p, stop
Model listGET /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

ProviderSber
TypeChat and text generation
Context131K tokens
InputText
OutputText
APIOpenAI-compatible
Tool callingNot declared
Service promptAbout 11 tokens per request
ProcessingIn Russia

What GigaChat 2 Max is good for

  • Keeping existing chatbots and assistants in Russian running
  • Integrations whose prompts are tuned to GigaChat 2

What to keep in mind with GigaChat 2 Max

If you are on it, count the cost of moving: usually it is enough to change the model name and run your tests. With a sixfold difference on input, the move pays off in the first month.

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 GigaChat 2 Max”: 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.

GigaChat 2 Max for companies outside Russia

GigaChat 2 Max, the previous GigaChat generation: a 131K context, kept for integrations already tuned to it. 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 GigaChat 2 Max and over a hundred other models with one key.

Contract and payment. Your contract and payment are with Kosareva Cloud LLC (Armenia), not with the model vendor. You are responsible for compliance with the rules of your jurisdiction; if in doubt, check with your counsel.

Requests to GigaChat 2 Max are processed in Russia. If data protection rules apply to you, assess the transfer before you send personal data.

Other GigaChat models

Price per 1M input tokens. Output prices and a monthly estimate for each — on the GigaChat page.

GigaChat 2 Max questions

How much does GigaChat 2 Max cost?

$9.32 per 1M tokens for both input and output: 797.07 ₽ in the catalog, converted at 85.5 ₽ per $1 (ID Bank’s non-cash rate on 3 October 2026). The vendor’s service prompt adds about 11 input tokens to each request. You pay only for the tokens you use.

How do I connect GigaChat 2 Max by API?

Register at kosareva.cloud, create a key, set base_url https://api.kosareva.cloud/v1 and the model gigachat-2-max in the standard OpenAI SDK.

What is the context size of GigaChat 2 Max?

131,072 tokens, shared between the prompt and the answer.

Who is GigaChat 2 Max for, and where is it weaker?

Only integrations already tuned to it. For new development it loses to GigaChat 3.5 Ultra on price, context (131,072 against 262,144 tokens) and features: tool calling is not declared for it.

Which models should I compare GigaChat 2 Max with?

With GigaChat 3.5 Ultra ($1.58 / $4.73): Ultra is six times cheaper on input, twice on output and has twice the context. GigaChat 2 Max has almost no service prompt (11 tokens), but that does not make up the difference.

Why does the dashboard show more input tokens than I sent?

The vendor adds its own service prompt to every request to GigaChat 2 Max, and it is billed as input: about 11 tokens by our measurement on 20 September 2026. Look at the actual input tokens in the dashboard before you estimate a monthly bill.

Where are requests to GigaChat 2 Max processed?

In Russia. If data protection rules apply to you, assess the transfer before sending personal data. You are responsible for compliance with the rules of your jurisdiction.

Can a company in the EU use GigaChat 2 Max?

Yes. Your contract and payment are with Kosareva Cloud LLC (Armenia), not with the model vendor. Whether your own compliance rules allow it is for you to check, with your counsel if needed.

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.

Connect GigaChat 2 Max in a couple of minutes

Get an API key and call GigaChat 2 Max through an OpenAI-compatible endpoint. Companies outside Russia pay by USD invoice. Questions: ceo@kosareva.cloud or @kosareva_cloud in Telegram.