Voyage Rerank 2.5
Voyage Rerank 2.5 is Voyage AI by MongoDB'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 is subject to Voyage AI by MongoDB's Terms & Privacy Policies.
- Input price
- Input $0.05, Per 1M tokens
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.', ],})Copy link to headingProviders
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.
| Provider |
|---|
| 32K | $0.05/M | 08/11/2025 |
Copy link to headingMore models by Voyage AI by MongoDB
| Model |
|---|
| 32K | $0.06/M | — |  | 01/15/2026 | ||||||||||
| 32K | $0.12/M | — | | 01/15/2026 | ||||||||||
| 32K | $0.02/M | — | | 01/15/2026 | ||||||||||
| 32K | $0.02/M | — | | 08/11/2025 | ||||||||||
| — | $0.02/M | — | | 05/20/2025 | ||||||||||
| — | $0.18/M | — | | 12/04/2024 |
Copy link to headingAbout Voyage Rerank 2.5
Voyage Rerank 2.5 is Voyage AI by MongoDB'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.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Voyage Rerank 2.5 is the quality-optimized tier of the Voyage AI by MongoDB 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 by MongoDB 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: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen 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
Copy link to headingConclusion
Voyage Rerank 2.5 delivers the highest retrieval accuracy in Voyage AI by MongoDB'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.
Copy link to headingFrequently Asked Questions
What is instruction-following in Voyage Rerank 2.5?
Instruction-following lets you steer relevance scores with natural language. You pass an instruction along with the query and candidate documents, and Voyage Rerank 2.5 adjusts scoring to reflect the instruction. On the MAIR benchmark, this capability lifts Voyage Rerank 2.5 12.70% above Cohere Rerank v3.5.
What is the difference between Voyage Rerank 2.5 and rerank-2.5-lite?
Voyage Rerank 2.5 is the quality-optimized tier and
rerank-2.5-liteis the latency-and-quality balanced tier. Both support instruction-following and the same context window of 32K tokens. Choose Voyage Rerank 2.5 when top-result accuracy is the priority; choosererank-2.5-litewhen per-query cost or latency matters more.How does Voyage Rerank 2.5 compare to Cohere Rerank v3.5?
Across 93 retrieval datasets, Voyage Rerank 2.5 improves accuracy by 7.94% over Cohere Rerank v3.5. Averaged across four first-stage retrieval methods, it outperforms Cohere Rerank v3.5 by 3.26% on NDCG@10 and by 12.70% on the MAIR instruction-following benchmark.
What is the context window for Voyage Rerank 2.5?
32K tokens. That is double the window of
rerank-2and eight times that of Cohere Rerank v3.5, so longer query-document pairs fit a single rerank call without truncation.Which first-stage retrievers does Voyage Rerank 2.5 work with?
Voyage Rerank 2.5 reorders candidates from any first-stage method. Voyage AI by MongoDB benchmarks it on BM25 lexical search, OpenAI
text-embedding-3-large,voyage-3-large, andvoyage-3.5. You can keep your existing embedding model and add Voyage Rerank 2.5 as a second-stage reranker.Does Voyage Rerank 2.5 support multilingual retrieval?
Yes. Voyage Rerank 2.5 reranks across many languages without separate per-language models. Voyage AI by MongoDB reports consistent improvement across all evaluated languages and first-stage retrieval methods.
How do I access Voyage Rerank 2.5 through Vercel AI Gateway?
Add your Voyage AI by MongoDB API key in AI Gateway settings, then send rerank requests through AI Gateway. AI Gateway authenticates requests and records usage. You can call Voyage Rerank 2.5 through the AI SDK alongside Chat Completions, Responses, and Messages API formats.
Is Zero Data Retention available for Voyage Rerank 2.5?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.