Getting started with the TextCortex API
Whether you need text classification, generation, or other AI language capabilities for personal or business use, you can exponentially boost your productivity with the power of large language models – without the headache of managing a complex infrastructure.
How does our API work?
Please note that our API isn't included in any of our plans: we only offer $1 worth of API credits once users sign up, when they're done with that they need to top-up their credits.
The API is charged on a per token basis. You can find our documentation here.
We charge $0,12 per 1K tokens.
We encourage users to start building with our free initial credits, as they would be enough to process around 125k tokens.
What is a token?
Tokens can be thought of as pieces of words. Before the API processes the request, the input is broken down into tokens. These tokens are not cut up exactly where the words start or end - tokens can include trailing spaces and even sub-words.
Here are some helpful rules of thumb for understanding tokens in terms of lengths:
- 1 token ~= 4 chars in English.
- 1- token ~= ¾ words.
- 100 tokens ~= 75 words.
Or
- 1-2 sentence ~= 30 tokens.
- 1 paragraph ~= 100 tokens.
- 1,500 words ~= 2048 tokens.
We only charge based on the token count of a generated output.
So, for example, if the summary of a 5000-word article equals to a 1,500-word output/summary (2048 tokens) and considering the pricing we have is $0,12 per 1000 tokens, that would make:
2048 / 1000 = 2,048
0,12 * 2,048 = $0,24576 charged for this single operation with an output of 1500-word summary.
How can I recharge my API credits?
You can add new credits in the APl Key section of the TextCortex Platform.