Using Models Developed by ZeroEntropy
zerank-1
and zerank-1-small
are reranker models developed by ZeroEntropy.
zerank-1
is our flagship state-of-the-art reranker, you can read more about its performance and cost in this blog post.
Both these models can be called using:
reranker
query parameter into top-snippetszerank-1-small
under an Apache 2.0 license, and it is also available through HuggingFace and Baseten.Our flagship model zerank-1
can be downloaded from HuggingFace under a non-commercial license. To use in a commercial setting, contact us at founders@zeroentropy.dev and we’ll get you a license ASAP!2,000,000 UTF-8 bytes per minute
.
A reranker request consumes bytes based on the number of documents and the total length of the input. The formula is:
$0.025/1M tokens
.
If you use the reranker as a standalone API, we will invoice you based on your usage.