Google Gemini
Free tier available
The easiest way to start: Google AI Studio offers a free tier that’s more than enough for everyday text correction.
Cost per correction : Free within Google AI Studio’s free tier, which is enough for everyday use. Beyond that, with Gemini 2.5 Flash-Lite: about $0.0002 per correction, i.e. ~$0.23 per 1,000 corrections.
- 1
Open Google AI Studio and sign in with your Google account.
- 2
Click “Get API key” in the top-left.
- 3
Click “Create API key”, then agree to create or select a Google Cloud project if prompted.
- 4
Your key appears (it starts with “AIza…”). Click the copy icon.
- 5
Paste it into Correctify’s options, in the “API key” field. Done.
OpenAI (ChatGPT)
Credit / payment card required
To use OpenAI’s models (the same as ChatGPT). API usage is billed per use: you need to add a payment method and a little credit.
Cost per correction : With GPT-4o mini (fast and inexpensive): about $0.0003 per correction, i.e. ~$0.35 per 1,000 corrections.
- 1
Create an account (or sign in) on the OpenAI platform.
- 2
In “Billing”, add a payment method and a small amount of credit (correcting text only costs a few cents).
- 3
Open the “API keys” page, then click “Create new secret key”.
- 4
Give it a name, confirm, then copy the key IMMEDIATELY (it starts with “sk-…”): it will never be shown again.
- 5
Paste it into Correctify’s options, in the “API key” field.
Anthropic (Claude)
Credit / payment card required
To use Anthropic’s Claude models. Like OpenAI, the API is billed per use: add a little credit to your account.
Cost per correction : With Claude 3.5 Haiku (Anthropic’s cheapest model): about $0.002 per correction, i.e. ~$2.10 per 1,000 corrections.
- 1
Create an account (or sign in) on the Anthropic console.
- 2
In “Billing” (Plans), add a payment method and some credit.
- 3
Open “API Keys”, then click “Create Key”.
- 4
Name the key, confirm, then copy it (it starts with “sk-ant-…”): keep it safe, it’s shown only once.
- 5
Paste it into Correctify’s options, in the “API key” field.
Estimates for a ~200-word text, using the models Correctify actually uses (Gemini 2.5 Flash-Lite, GPT-4o mini, Claude 3.5 Haiku). The math counts both the request (instructions + text ≈ 650 tokens) and the response (corrected text + list of fixes ≈ 400 tokens). Prices as of early 2026, subject to change.
