Since Keras API as defined as layers, how would it be used to implement the word2vec?
Your question is really broad.. But there are many manuals and tutorials which describe how to do it step by step.
My personal favorite would be:
Practical Text Classification With Python and Keras - It has a very detailed explanation of every step of the implementation while remaining practical.
You can also try:
A Word2Vec Keras tutorial - This one focuses more on understanding how word2vec embedding works, but it also contains an implementation.
Tensorflow released a version, however, it's missing negative sampling, which is very important in word2vec