MMOOZZGG.com

Calculator

LLM API cost calculator: your token bill per month

4 min read12 sources

Cloud models sell tokens, not servers. The LLM API cost calculator turns your scenario, requests per day and the length of the request and answer, into a monthly bill at the prices of foreign and Russian providers as of 29 September 2026, at the Bank of Russia exchange rate. You can edit the prices and the rate right in the form.

On this page · 5 sections

Calculator

Cloud API bill per month

Volume per month

  • Input tokens45 million
  • Output tokens15 million
  • Total60 million

The token count depends on the model: for one Russian cloud model, its developer reports 3–4 characters per token on average; for other models, measure your own text with the provider's counter. Russian models bill input and output at one price.

Bill by model, cheapest first

  • GPT-6 Luna$12.00
  • Gemini 3.1 Flash-Lite$33.75
  • Russian provider B, Lite model, sync$46.20
  • Russian provider A, Lite model, async$71.08
  • Gemini 3.8 Flash (promo until 31 Dec 2026)$90.00
  • GPT-5.4 mini$101
  • Claude Haiku 4.5$120
  • Russian provider A, Lite model, sync$142
  • Russian provider B, Max model, async$231
  • Claude Sonnet 5.5$240
  • GPT-6 Sol$240
  • Gemini 3.1 Pro (up to 200k)$270
  • Russian provider B, Pro model, sync$355
  • Russian provider A, Pro model, async$434
  • Russian provider B, Max model, sync$462
  • Claude Opus 5.5$480
  • GPT-5.5$675
  • Russian provider A, Pro model, sync$853
  • Claude Fable 5.1$1,200
  • GPT-6 Astra$1,200

Defaults come from the sources as of 29 September 2026. Dollar figures use the official US dollar rate set by the Bank of Russia, the country's central bank: 84.41. The estimate is approximate; every field can be edited.

How it calculates

Input tokens per month: requests per day, multiplied by 30 and by the request length with context. Output tokens: requests multiplied by the answer length. The bill: input tokens multiplied by the price per million input tokens, plus output tokens at the output price, in US dollars. Russian models are priced per 1,000 tokens, with the same price for input and output, and are converted at the Bank of Russia rate of 84.4 per US dollar on 29 September 2026. The number of tokens depends on the model: per data from a large Russian bank, its model averages 3–4 characters per token, while other models give their own count for the same phrase. Measure a typical request with the provider’s token counter.

Prices in the calculator as of 29 September 2026

Foreign models, US dollars per million tokens, input and output: Claude Fable 5.1 10 and 50, Opus 5.5 4 and 20, Sonnet 5.5 2 and 10, Haiku 4.5 1 and 5, batch mode minus 50%. OpenAI GPT-6 Astra 10 and 50, GPT-5.5 5 and 30, GPT-6 Sol 2 and 10, GPT-5.4 mini 0.75 and 4.50, GPT-6 Luna 0.10 and 0.50. Gemini 3.1 Pro 2 and 12, and 4 and 18 above 200,000 tokens of context; Gemini 3.8 Flash 0.75 and 3.75 on a promotion until 31 December 2026; 3.1 Flash-Lite 0.25 and 1.50. Russian models, per million tokens: a large Russian tech company’s Pro model $14 in sync mode and $7 in async mode, its Lite model $2 and $1; a large Russian bank’s Max model $8, Pro $6, Lite about $0.80, half price in async mode; the Pro package of 50 million tokens for $300 costs the same as sync mode.

Example: 1,000 requests a day

A support agent: 1,000 requests a day, 1,500 input tokens with history and 500 output tokens, for a total of 45 million input and 15 million output tokens a month. The bill: GPT-6 Luna $12, Gemini 3.1 Flash-Lite $34, the bank’s Lite model $47, Gemini 3.8 Flash $92, GPT-5.4 mini $100, Haiku 4.5, $100, the tech company’s Lite model $150, Sonnet 5.5 and GPT-6 Sol $250 each, Gemini 3.1 Pro $250, the bank’s Pro model $350, the bank’s Max model $450, Opus 5.5, $500, GPT-5.5, $700, the tech company’s Pro model $900, Fable 5.1 and GPT-6 Astra $1,200 each. A hundredfold spread for one scenario: the choice of model matters more than the choice of provider.

What else affects the bill

Context caching lowers the price of the repeated part of a request at large foreign providers, and the calculator counts it as a discounted share of the input. Batch or async mode for overnight processing gives minus 50% at Claude and at both Russian providers; check the terms with other providers. Paying for foreign APIs from Russia: the services do not work directly, Russian addresses are not on the lists of supported regions, and the payment goes through an intermediary with a commission. Add it in the commission field.

How to read the result

Compare the bill with the result of the local AI calculator at the same volume. At 60 million tokens a month on a cheap model, the cloud costs $12 to $100, and by our calculation no configuration in the local AI calculator pays back within 36 months. On flagship models at $1,200 a month, a workstation with one card pays back in about 17 months if the local model solves the same task; that is a separate question you check with a pilot.

Questions and answers

Why are prices in dollars?

Foreign providers bill in US dollars. Russian models are priced per 1,000 tokens, and the calculator converts them at the Bank of Russia rate on the check date; you can change the rate in the field.

How many tokens are in one request?

Count from characters: per data from a large Russian bank, its model averages 3–4 characters per token, so a page of 1,800 characters is about 450–600 tokens, and a 10-page document about 4,500–6,000. Other models give their own count on the same text: measure your typical request with the provider’s token counter.

Sources and fact-checking

Checked by the editors on 29 September 2026.

  1. Central Bank of Russia, exchange rates as of 29 September 2026 (cbr.ru)
  2. Claude Platform, API prices (checked 29 September 2026) (platform.claude.com)
  3. Puter, review of OpenAI API prices based on openai.com, 29 September 2026 (developer.puter.com)
  4. Puter, review of Gemini API prices, 8 September 2026 (developer.puter.com)
  5. kalinkindev.ru, YandexGPT API prices per Yandex Cloud billing, 13 September 2026 (kalinkindev.ru)
  6. Sber Developers, GigaChat API rates for legal entities, 16 September 2026 (developers.sber.ru)
  7. Habr, Sber: GigaChat API prices cut threefold, 4 February 2026 (habr.com)
  8. Claude Platform, supported regions (checked 29 September 2026) (platform.claude.com)
  9. OpenAI, API supported countries (checked 29 September 2026) (developers.openai.com)
  10. Sber Developers, GigaChat token counting: 3–4 characters per token on average, 17 July 2026 (developers.sber.ru)
  11. Bank of Russia, official US dollar rate as of 29 September 2026 (cbr.ru)
  12. Yandex AI Studio, rates, 30 September 2026 (aistudio.yandex.ru)

Found a mistake? Tell us

Publications

Contact us