AI Models and Cost

You bring your own API key, and the engine bills you directly at its published rates — the plugin
adds nothing on top and never handles your money.

Which engine and model you pick under AI Translation → Settings → General decides both the
quality and the bill. The engines themselves are described in Translation Engine – AI Providers.

#Models per engine

The free version ships the cheapest models of each engine. PRO adds the rest, for content where the
cheap models struggle — marketing copy that has to land, legal or medical text, anything where tone
matters more than throughput.

#Reasoning effort

Settings → General → Reasoning Effort controls how much thinking a language model does before
answering. Higher effort improves quality on difficult passages, and costs more and takes longer.
Low is the default and is the right choice for most content. Machine-translation engines ignore it.

#What it actually costs

Language models are billed per token — roughly, per chunk of text in and out. As a rough guide, a
single 1,000-word page through GPT-5.4 Nano costs well under one cent. Google Translate and DeepL
are billed per character sent. MyMemory is free within its daily quota.

You do not have to rely on estimates. Every finished job records what it actually cost, priced
against the model that produced it, and AI Translation → History shows real figures for your own
content. The Dashboard totals the last 30 days.

#Cost history and PRO

Prices for the PRO models are kept even when the licence is not active, deliberately.

If your licence lapses, the PRO models disappear from the model list — but the cost already recorded
for translations made with them stays correct. Cost history is a record of what you spent, not a
feature to be switched off.

#Keeping the bill down

• Write a website description. Better context means fewer retranslations, which is the cheapest
  saving available.
• Use Batch processing for work that does not have to be done now: about half the price, on
  OpenAI and Claude. See Translation Engine – AI Providers.
• Update, do not re-translate. With PRO, editing an already translated post and translating it
  again sends only what changed. See Updating Outdated Translations.
• Translate what you need. Target languages are chosen per translation, not set once globally.
• Start on the cheapest model and move up only for the content that visibly needs it. There is
  no reason to pay reasoning-model prices for a page of product specifications.
• Set a spending limit on your provider account. The plugin cannot do this for you, and it is
  the only hard stop that exists. For automatic translation, PRO adds daily limits of its own — see
  Automatic Translation.