Voyage Rerank 2.5
Voyage Rerank 2.5 is Voyage AI's generalist reranker optimized for retrieval quality. It supports a context window of 32K tokens, instruction-following over natural language steering, and multilingual reranking. On 93 retrieval datasets, it improves accuracy by 7.94% over Cohere Rerank v3.5. Your use subject to Voyage AI's Terms & Privacy Policies.
import { rerank } from 'ai';
const result = await rerank({ model: 'voyage/rerank-2.5', query: 'What is the capital of France?', documents: [ 'Paris is the capital of France.', 'Berlin is the capital of Germany.', 'Madrid is the capital of Spain.', ],})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
More models by Voyage AI
| Model |
|---|
| 32K | $0.12/M | — |  | 01/15/2026 | ||||||||
| 32K | $0.02/M | — | | 01/15/2026 | ||||||||
| 32K | $0.06/M | — | | 01/15/2026 | ||||||||
$0.02/M | — | | 05/20/2025 | |||||||||
$0.06/M | — | | 05/20/2025 | |||||||||
$0.12/M | — | | 04/15/2024 |
About Voyage Rerank 2.5
Voyage Rerank 2.5 is Voyage AI's generalist reranker released August 11, 2025. It reorders candidate documents returned by a first-stage retriever to lift top-k relevance, with a context window of 32K tokens, multilingual support, and instruction-following capabilities new to the rerank family.
Across 93 retrieval datasets, Voyage Rerank 2.5 improves accuracy by 7.94% over Cohere Rerank v3.5 when paired with four different first-stage methods: BM25 lexical search, OpenAI text-embedding-3-large, voyage-3-large, and voyage-3.5. Averaged across these first-stage retrieval methods, Voyage Rerank 2.5 outperforms Cohere Rerank v3.5, Qwen3-Reranker-8B, and rerank-2 by 3.26%, 2.34%, and 1.35% respectively on NDCG@10.
Instruction-following lets you steer relevance scores using natural language. You can describe the kind of relevance you want ('prefer documents that cite primary sources' or 'rank legal precedents above commentary') and Voyage Rerank 2.5 adjusts its scoring accordingly. On the Massive Instructed Retrieval (MAIR) benchmark, Voyage Rerank 2.5 outperforms Cohere Rerank v3.5 by 12.70%. The context window of 32K tokens is double that of rerank-2 and eight times that of Cohere Rerank v3.5, so longer query-document pairs fit a single rerank call without truncation.
What To Consider When Choosing a Provider
- Configuration: Voyage Rerank 2.5 is the quality-optimized tier of the Voyage AI 2.5 reranker series. Pick it when reranking quality is the primary constraint and per-query cost is secondary. For workloads where latency and cost dominate,
rerank-2.5-litereaches similar accuracy at a lower price tier. - Configuration: Use instructions to encode policy that's awkward to express in retrieval embeddings. Voyage Rerank 2.5 accepts free-form instructions such as 'prefer recent regulatory filings' or 'down-rank marketing pages' and adjusts scoring without requiring index rebuilds.
- Configuration: Voyage Rerank 2.5 pairs with any first-stage retriever. Voyage AI benchmarks it on top of BM25, OpenAI
text-embedding-3-large,voyage-3-large, andvoyage-3.5. You can keep your existing embedding stack and add Voyage Rerank 2.5 as a second-stage reranker. - Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Voyage Rerank 2.5
Best for
- High-stakes retrieval: Customer-facing search, legal discovery, and compliance flows where the top result quality directly affects outcomes
- Instruction-driven relevance: Encode preferences such as recency, source authority, or topical focus in natural language without retraining embeddings
- Multilingual reranking: A single reranker covers retrieval across many languages without per-language models
- Long query-document pairs: The context window of 32K tokens fits lengthy filings and long documents in one rerank call
- RAG pipelines: Improve the top-k passed into the generator without changing the upstream embedding model
Consider alternatives when
- Cost and latency dominate:
rerank-2.5-litereaches similar accuracy at a lower price tier with reduced compute per query - Open-source-only constraint: Qwen3-Reranker-8B is available for self-hosting, though Voyage Rerank 2.5 outperforms it on Voyage's published benchmarks
- Single-language English-only retrieval: A monolingual reranker may suffice when no other languages are in scope
- No reranker stage needed: Strong first-stage retrievers like
voyage-3.5may meet your accuracy targets without a second pass
Conclusion
Voyage Rerank 2.5 delivers the highest retrieval accuracy in Voyage AI's 2.5 reranker series. Instruction-following, multilingual coverage, and a context window of 32K tokens make it suited for high-stakes RAG and search pipelines where the quality of the top results matters most. Route requests through AI Gateway to swap between Voyage Rerank 2.5 and rerank-2.5-lite as your accuracy and cost targets evolve.