by Qwen
Based on the dense foundational model of the Qwen3 series, it is specifically designed for ranking tasks. It inherits the base model’s outstanding multilingual capabilities, long-text understanding, and reasoning skills, achieving significant advancements in ranking tasks.
| Input | $0.07 / 1M tokens |
| Modalities | text, image |
Use bce-reranker-base via the AIHubMix unified API — one interface for every major LLM.