{"business":{"endpoints":["POST /v1/rerank"],"host":"rerank.mojojojo.cc","kind":"model","live":true,"meters":[{"free_per_month":1,"id":"model.rerank.pairs","label":"Query-document pairs","unit":"1k pairs","usd_per_unit":0.01}],"model":"cross-encoder/ms-marco-MiniLM-L6-v2 (Apache-2.0), revision 233902d2","notes":["Scores are raw cross-encoder logits (higher is more relevant); not comparable across queries.","Up to 512 documents per request; each document is truncated to 512 tokens with the query.","Max logit difference to PyTorch 2.9e-06.","Speed: 0.34x PyTorch at batch 1, 0.89x at batch 200. English MS MARCO passages only; evaluate on your own data."],"pitch":"Cohere-style reranking with the MiniLM-L6 cross-encoder on Mojo CPU kernels, $10 per million pairs","repo":"https://github.com/lee101/mojobusinesses","slug":"rerank","status":"built","title":"Rerank API"},"ok":true}