Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | cohereCohere: Rerank v3.5Remove × | voyageaiVoyageAI by MongoDB: rerank-3Remove × | nvidiallama-nemotron-rerank-vl-1b-v2Remove × |
|---|---|---|---|
| What’s different | Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword… | 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,... | The llama-nemotron-rerank-vl-1b-v2 is a 1.7B parameter multimodal reranking model designed to evaluate and order the relevance of document images and text against specific user queries. It excels at… |
| Date | Apr 5, 2026Listed | Sep 30, 2026Listed | Mar 12, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | See provider quotes | See provider quotes | See provider quotes |
| Provider endpoints | 0 endpoints → | 0 endpoints → | 0 endpoints → |
Specifications | |||
| Context window | 4.1K | 32K | 10.2K |
| Max output | 3.7K | 28.8K | — |
| Parameters | — | — | 1B |
Add another model
Search all models →nvidiaNVIDIA: Nemotron 3.5 Rerank 8B (free)nvidiaNemotron-3.5-Rerank-8B-BF16voyageaiVoyageAI by MongoDB: rerank-3-litevoyageaiVoyageAI by MongoDB: rerank-2.5-litevoyageaiVoyageAI by MongoDB: rerank-2.5nvidiaNVIDIA: Llama Nemotron Rerank VL 1B V2 (free)cohereCohere: Rerank 4 ProcohereCohere: Rerank 4 Fast