Melhores modelos de reclassificação para pesquisa e RAG
Classificações de modelos atualizadas com base em dados reais de uso.
Os modelos são classificados pelo total de tokens de prompt e de resposta processados pela API do OpenRouter nos últimos 7 dias. Exibindo os 10 melhores modelos. As classificações medem o uso no OpenRouter e refletem a adoção, não a qualidade do modelo ou o desempenho em testes de referência.
Os modelos de reclassificação reordenam documentos candidatos, trechos ou resultados de pesquisa por relevância, aprimorando a etapa de recuperação na pesquisa semântica, na geração aumentada por recuperação (RAG) e nos pipelines de recomendação. Esta coleção classifica os modelos de reclassificação pelo uso no OpenRouter na última semana. Os melhores modelos atualmente são rerank-2.5-lite, rerank-2.5 e rerank-3-lite. Compare preços, latência e qualidade para encontrar a melhor opção para seu pipeline de pesquisa ou RAG.
Principais modelos de reclassificação no OpenRouter

VoyageAI by MongoDB: rerank-2.5-lite
rerank-2.5-lite is a reranker optimized for both latency and quality, delivering a 7.16% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 10.36% on the Massive Instructed Retrieval Benchmark (MAIR). The model supports a combined context length of 32K tokens per query–document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-2.5-lite supports instruction following, allowrerank-2.5-lite here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-2.5
rerank-2.5 is a cutting-edge reranker optimized for quality, delivering a 7.94% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets. It also outperformed Cohere Rerank v3.5 by 12.70% on the Massive Instructed Retrieval Benchmark (MAIR). The model supports a combined context length of 32K tokens per query–document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-2.5 supports instruction following, allowingbout rerank-2.5 here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-3-lite
rerank-3-lite is a reranker optimized for both latency and quality and a drop-in upgrade to rerank-2.5-lite, improving on it by 0.94% NDCG@10 on average across domain evaluations and by 1.86% on long-document evaluations, with code retrieval gains of 2.77% atop voyage-3-large and 2.59% atop voyage-4-large. It matches the retrieval quality of rerank-2.5, and across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 1.44% and Qwen3-Reranker-8B by 2.61%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3-lite supports instruction following, allowing users to guide relevance scoring t rerank-3-lite here: mongodb.com/products/platform/ai-search-and-retrieval/models

VoyageAI by MongoDB: rerank-3
rerank-3 is a reranker optimized for quality and a drop-in upgrade to rerank-2.5, improving on it by 0.80% NDCG@10 on average across domain evaluations and by 3.35% on long-document evaluations, with code retrieval gains of 2.01% atop voyage-3-large and 1.96% atop voyage-4-large. Across 93 retrieval datasets it outperforms Cohere Rerank v4.0 Pro by 2.14% and Qwen3-Reranker-8B by 3.31%. The model supports a combined context length of 32K tokens per query-document pair, including up to 8K tokens for the query, enabling more accurate retrieval over longer documents. Additionally, rerank-3 supports instruction following, allowing users to guide relevance sco about rerank-3 here: mongodb.com/products/platform/ai-search-and-retrieval/models

Qwen3 Reranker 8B
Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG pipelines. Supports 100+ languages and programming languages, with instruction-aware reranking that allows customizing scoring criteria per task. Offers strong performance on multilingual benchmarks including MTEB, CMTEB, and MMTEB.

Cohere: Rerank 5 Fast
Rerank 5 Fast is the low-latency tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for high-throughput retrieval such as high-volume search, agent tool loops, and first-pass filtering before a more expensive step.
Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Pro is the higher-accuracy sibling for complex queries and long or domain-specific documents.

Cohere: Rerank 5 Pro
Rerank 5 Pro is the higher-accuracy tier of Cohere's Rerank 5 family of reranking models. It scores and reorders candidate documents against a query and is suited for retrieval pipelines where ranking quality matters most: complex or reasoning-heavy queries, long or domain-specific documents, and RAG systems that feed a small number of passages to a generator.
Relevance scores are calibrated to a 0-1 range so a fixed threshold behaves consistently across queries. Rerank 5 Fast is the lower-latency sibling for high-volume search and agent loops.
NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)
Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG pipelines handling charts, tables, infographics, and mixed-media documents. Functions as a cross-encoder that accepts text queries paired with image, text, or combined document inputs, delivering approximately 6-7% recall improvements over embedding-only baselines on visual document retrieval benchmarks.
NVIDIA: Nemotron 3.5 Rerank 8B (free)

Qwen3 Reranker 0.6B
Qwen3 Reranker 0.6B is the smallest text reranking model from Alibaba Cloud in the Qwen3 Reranker series. Built on the Qwen3 architecture, it evaluates query-document pairs to produce relevance scores for retrieval and RAG pipelines. Supports 100+ languages with instruction-aware reranking. Designed for low-latency, resource-constrained deployments.
Perguntas frequentes
Envie POST /api/v1/rerank com o slug do modelo, sua query, um array documents e, opcionalmente, top_n. A resposta retorna results com um relevance_score e um index para cada documento. O guia prático de RAG explica a requisição passo a passo.
As listagens com preços publicados cobram por unidade de pesquisa ou por token de entrada, dependendo do modelo, portanto compare os preços na mesma unidade antes de escolher. Você paga apenas pelas requisições que faz, sem assinatura separada por provedor.
Recupere trechos candidatos com um modelo de embeddings, reordene os principais candidatos para aumentar a precisão e, em seguida, passe os melhores documentos a um LLM como contexto. Todas as três etapas usam a mesma chave de API do OpenRouter.
Sim. Uma única chave de API do OpenRouter funciona para todos os modelos de reclassificação desta página e para todos os outros modelos no OpenRouter. Crie uma chave na sua página de chaves de API.