Skip to contentК содержанию
LLMcode
ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияNewsНовости
ENRU
EnglishРусский
Sign inВойтиCreate accountСоздать аккаунтAccountАккаунт
MenuМеню
ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияNewsНовостиCreate accountСоздать аккаунт
LLMcode

Model names in the API are LLMcode profiles with their own routing. They do not mean direct access to the same-named models of OpenAI LLC or Anthropic PBC. Trademarks belong to their owners. The service is independent and is not affiliated with OpenAI or Anthropic.Названия моделей в API — профили LLMcode с собственной маршрутизацией. Они не означают прямой доступ к одноимённым моделям OpenAI LLC или Anthropic PBC. Товарные знаки принадлежат их правообладателям. Сервис независим и не аффилирован с OpenAI/Anthropic.

CatalogКаталог

ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияKey checkПроверка ключа

LegalДокументы

OfferОфертаPrivacyКонфиденциальностьConsentСогласиеAcceptable useДопустимое использованиеRefundВозврат

LearnМатериалы

GuidesГайдыComparisonsСравненияAlternativesАльтернативыIntegrationsИнтеграцииUse casesСценарииGlossaryГлоссарийNewsНовостиRSSTelegramTelegram-канал
HomeГлавнаяModelsМоделиPricingЦеныSign inВойтиAccountАккаунт
LLMcode/Glossary/Per-1M-token pricing, explained

Glossary

Per-1M-token pricing, explained

Model prices are quoted in USD per 1 million tokens. A request is billed by counting input, output and cached-input tokens separately, then multiplying by each rate.

Updated 2026-11-16

Input, output and cache

Input tokens are everything sent to the model: the system prompt, the messages and the tools. Output tokens are what the model generates.

Cached input is a cheaper rate applied when the provider recognizes repeated prefix tokens. The gateway cannot force caching; it applies the cache rate only when the provider reports cached tokens.

How a request is billed

Tokens in each bucket are counted, divided by 1,000,000, and multiplied by the corresponding per-1M rate. Fractions of a million still cost their share.

The applied price is a snapshot stored with the request journal entry, so a later price change never rewrites what you already spent.

Why per-1M and not per-request

A per-request price cannot scale: a one-line reply and a forty-page analysis cost the provider differently. Tokens are the unit that tracks real work.

Comparing models is only meaningful at the token level, on the same bucket. The /models table lists input, output and cache side by side.

Published model prices

USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.

ModelInputOutputCache
Claude Opus 5.5$2.70$8.00$0.14
DeepSeek Flash$0.50$2.00$0.01
Claude Sonnet 5.5$1.33$6.67$0.07
DeepSeek V4 Pro$2.20$6.60$0.07

Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.

Questions

How many characters is one token?

Roughly four characters of English text, but it varies by model and script. Treat it as an approximation, not a conversion constant.

Is the cache rate always applied?

No. It applies only when the provider reports cached input tokens for that request.

Where do I see the applied price?

In /account/logs each request shows the model, token counts and the applied price per bucket.

Does 1 USD equal 1,000,000 UT?

Yes. UT is the internal accounting unit; 1 USD = 1,000,000 UT.

See also

Models and pricesPricing and top-upSetup instructionsAPI docs

One key for every model

OpenAI- and Anthropic-compatible endpoints, balance in USD, top-up from $10.

Create accountPricing
Base URL
https://llmcode.io/v1
Key format
sk-llmcode-…