voyageai logo
voyageai

VoyageAI by MongoDB: rerank-2.5

Descrição da fonte (inglês)

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%...

Visão geral

Especificações do modelo

Contexto
32.000 tokens
Saída máxima
28.800 tokens
Arquitetura
text->rerank
Tokenizador
Other
Limite de conhecimento
Não informado
Moderado
Não
OPENROUTER

Preços completos

Tarifas sincronizadas do OpenRouter, por milhão de tokens.

Entrada
$0.05
por milhão de tokens de entrada
API

Início rápido

Defina OPENROUTER_API_KEY localmente. Python requer requests; JavaScript roda em Node.js. Mantenha a chave no servidor.

Documentação da API

curl --fail-with-body https://openrouter.ai/api/v1/rerank \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"voyageai/rerank-2.5","query":"What is the capital of France?","documents":["Paris is the capital of France.","Berlin is the capital of Germany."],"top_n":1}'
Recursos e modalidades

EntradaSaída

Entrada
text
Saída
rerank
API

Parâmetros de API compatíveis

Provedores disponíveis

1 Provedor

Verificado: 7 de setembro de 2026

Provedores ao vivo no OpenRouter

Disponibilidade, latência, throughput e roteamento mudam continuamente. Consulte a fonte para dados atuais.

OpenRouter

VoyageAI by MongoDB

Não informado
Contexto
32K
Saída máxima
29K
voyageai

4 modelos

Todos os modelos
voyageai logovoyageai

VoyageAI by MongoDB: voyage-code-4

voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048, 1024, 512, and 256...

Contexto
32K
Entrada
text
Saída
embeddings
Entrada: $0.12por milhão de tokens
Ver detalhes do modelo
voyageai logovoyageai

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...

Contexto
32K
Entrada
text
Saída
rerank
Entrada: $0.02 por milhão de tokens de entrada
Ver detalhes do modelo
voyageai logovoyageai

VoyageAI by MongoDB: voyage-multimodal-3.5

voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for...

Contexto
32K
Entrada
text · image
Saída
embeddings
Entrada: $0.12por milhão de tokens
Ver detalhes do modelo
voyageai logovoyageai

VoyageAI by MongoDB: voyage-4-lite

voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings in 2048, 1024, 512, and 256 dimensions,...

Contexto
32K
Entrada
text
Saída
embeddings
Entrada: $0.02por milhão de tokens
Ver detalhes do modelo