Feature Request: Add Cross-Encoder Reranking Support via /rerank or /score Endpoint
It would be great to have native support for reranking in the Nebius AI API, especially for use in retrieval-augmented generation (RAG) or semantic search workflows.
See https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html for the /rerank and /score API.
Add a dedicated endpoint for reranking such as the /score or the /rerank endpoind.
Add cross-encoder models to the available model library
Log in to comment and vote
Comments2
Dmytro Polishchuk
Feb 7
Seems that there’s an endpoint in the docs already:
https://docs.tokenfactory.nebius.com/api-reference/inference/rerank-documents
But I didn’t find any models that support it currently on Nebius.
Milo
Jan 26
Agree we need rerank with embeddings. Please introduce Qwen/Qwen3-Reranker-8B with already offered Embedding