Meilleurs modèles de reclassement pour la recherche et le RAG
Classement des modèles mis à jour à partir de données d’utilisation réelles.
Les modèles sont classés selon le nombre total de jetons de prompt et de réponse traités via l’API OpenRouter au cours des 7 derniers jours. Affichage des 10 meilleurs modèles. Les classements mesurent l’utilisation sur OpenRouter et reflètent l’adoption, et non la qualité des modèles ou leurs performances aux tests de référence.
Les modèles de reclassement réordonnent les documents candidats, les passages ou les résultats de recherche par pertinence, affinant ainsi l’étape de récupération dans la recherche sémantique, la génération augmentée par récupération (RAG) et les pipelines de recommandation. Cette collection classe les modèles de reclassement selon leur utilisation sur OpenRouter au cours de la semaine écoulée. Les meilleurs modèles actuels sont rerank-2.5-lite, rerank-2.5 et rerank-3-lite. Comparez les tarifs, la latence et la qualité pour trouver le modèle le mieux adapté à votre pipeline de recherche ou de RAG.
Meilleurs modèles de reclassement sur 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: 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.
Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing required, and state of the art performance with low latency.
Questions fréquentes
Envoyez une requête POST /api/v1/rerank avec le slug du modèle, votre query, un tableau documents et, éventuellement, top_n. La réponse renvoie results avec un relevance_score et un index pour chaque document. Le guide pratique RAG détaille la requête.
Les offres dont les tarifs sont publiés sont facturées par unité de recherche ou par jeton d’entrée, selon le modèle, alors comparez les prix dans la même unité avant de choisir. Vous ne payez que les requêtes que vous effectuez, sans abonnement distinct par fournisseur.
Récupérez des fragments candidats avec un modèle d’embeddings, reclassez les meilleurs candidats pour affiner la précision, puis transmettez les meilleurs documents à un LLM comme contexte. Les trois étapes utilisent la même clé API OpenRouter.
Oui. Une seule clé API OpenRouter fonctionne avec tous les modèles de reclassement de cette page et avec tous les autres modèles sur OpenRouter. Créez une clé sur votre page des clés API.