Is there a pre-trained model that predict the next letter based on the previous letters?

Hi, I am curious if there is any model that does the following task:
input: a sequence of letters. For example “hell”
output: a vector that shows the possibilities of the following letter. In other words, a vector with a size of 27(26 English alphabet letters + 1 letter for the end of the word). For instance: a vector that has its maximum probability for the “o” letter.
that means the word is hello