{"message":null,"data":[{"name":"@cohere/rerank-5-fast","description":"Cohere\u0027s low-latency Rerank 5 tier for high-throughput retrieval, with a 32K context window.","releaseDate":"2026-11-03","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.02 per 1M tokens","sourceUrl":"https://cohere.com/rerank","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@cohere/rerank-5-pro","description":"Cohere\u0027s higher-accuracy Rerank 5 tier for retrieval pipelines where ranking quality matters most, with a 32K context window.","releaseDate":"2026-11-03","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://cohere.com/rerank","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@nvidia/nemotron-3.5-rerank-8b","description":"NVIDIA Nemotron 3.5 reranker for high-quality text relevance scoring.","releaseDate":"2026-10-21","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Rerank-8B-BF16","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":1024},"isDefault":false,"subscriptionUsage":false},{"name":"@voyageai/rerank-3","description":"Voyage AI\u0027s instruction-following multilingual reranker with a 32K context window.","releaseDate":"2026-09-30","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://blog.voyageai.com/2026/09/30/rerank-3/","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@voyageai/rerank-3-lite","description":"Voyage AI\u0027s low-cost multilingual reranker with a 32K context window.","releaseDate":"2026-09-30","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.02 per 1M tokens","sourceUrl":"https://blog.voyageai.com/2026/09/30/rerank-3/","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@jina/reranker-v3.5","description":"Jina\u0027s multilingual listwise reranker for long-context retrieval across more than 100 languages.","releaseDate":"2026-07-27","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://jina.ai/models/jina-reranker-v3.5","autonomousUse":true,"technicalInformation":{"contextSize":131072,"maxDocuments":null},"isDefault":false,"subscriptionUsage":false},{"name":"@nvidia/llama-nemotron-rerank-vl-1b-v2","description":"NVIDIA text and visual-document reranker used here for text relevance scoring.","releaseDate":"2025-12-18","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.01 per 1M tokens","sourceUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-nemotron-rerank-vl-1b-v2","autonomousUse":true,"technicalInformation":{"contextSize":10240,"maxDocuments":1024},"isDefault":false,"subscriptionUsage":false},{"name":"@cohere/rerank-4-fast","description":"Cohere\u0027s low-latency multilingual enterprise reranker with a 32K context window.","releaseDate":"2025-12-11","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.002/search unit","sourceUrl":"https://cohere.com/rerank","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@cohere/rerank-4-pro","description":"Cohere\u0027s highest-quality multilingual enterprise reranker with a 32K context window.","releaseDate":"2025-12-11","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.0025/search unit","sourceUrl":"https://cohere.com/rerank","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@jina/reranker-v3","description":"Jina\u0027s multilingual listwise reranker for long-context retrieval across more than 100 languages.","releaseDate":"2025-10-01","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://jina.ai/models/jina-reranker-v3","autonomousUse":true,"technicalInformation":{"contextSize":131072,"maxDocuments":null},"isDefault":false,"subscriptionUsage":false},{"name":"@qwen/qwen3-reranker-0.6b","description":"Compact multilingual Qwen3 reranker optimized for low-cost semantic relevance scoring.","releaseDate":"2025-06-05","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.01 per 1M tokens","sourceUrl":"https://qwenlm.github.io/blog/qwen3-embedding","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":1024},"isDefault":false,"subscriptionUsage":false},{"name":"@qwen/qwen3-reranker-4b","description":"Mid-sized multilingual Qwen3 reranker balancing retrieval quality, latency, and cost.","releaseDate":"2025-06-05","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.025 per 1M tokens","sourceUrl":"https://qwenlm.github.io/blog/qwen3-embedding","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":1024},"isDefault":false,"subscriptionUsage":false},{"name":"@qwen/qwen3-reranker-8b","description":"Largest Qwen3 reranker in the catalog for higher-quality multilingual semantic relevance scoring.","releaseDate":"2025-06-05","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.05 per 1M tokens","sourceUrl":"https://qwenlm.github.io/blog/qwen3-embedding","autonomousUse":true,"technicalInformation":{"contextSize":32768,"maxDocuments":1024},"isDefault":false,"subscriptionUsage":false},{"name":"@cohere/rerank-3.5","description":"Cohere\u0027s multilingual reranker for semantic and keyword retrieval across structured and unstructured data.","releaseDate":"2024-12-02","documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.001/search unit","sourceUrl":"https://cohere.com/blog/rerank-3pt5","autonomousUse":true,"technicalInformation":{"contextSize":4096,"maxDocuments":10000},"isDefault":false,"subscriptionUsage":false},{"name":"@aivax/reflex-v1","description":"AIVAX low-latency semantic reranker with bounded lexical evidence and account-scoped document caching.","releaseDate":null,"documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"$0.015 per 1M tokens (cache miss)\n$0.003 per 1M tokens (cache hit)","sourceUrl":null,"autonomousUse":true,"technicalInformation":{"contextSize":1948,"maxDocuments":10000},"isDefault":true,"subscriptionUsage":true},{"name":"lexical","description":"Applies a local word-aware boost using exact and fuzzy matches, query coverage, and term proximity.","releaseDate":null,"documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"No cost","sourceUrl":null,"autonomousUse":true,"technicalInformation":{"contextSize":null,"maxDocuments":null},"isDefault":false,"subscriptionUsage":false},{"name":"rrf","description":"Fuses semantic and lexical rank positions for candidates already retrieved by RAG.","releaseDate":null,"documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"No cost","sourceUrl":null,"autonomousUse":false,"technicalInformation":{"contextSize":null,"maxDocuments":null},"isDefault":false,"subscriptionUsage":false},{"name":"none","description":"Disables reranking and preserves vector similarity order.","releaseDate":null,"documentationUrl":"https://docs.aivax.net/docs/rag/reranking","pricingDescription":"No cost","sourceUrl":null,"autonomousUse":false,"technicalInformation":null,"isDefault":false,"subscriptionUsage":false}]}