Skip to content
Vercel April 2026 security incident
Read the bulletin
All Models

Voyage Finance 2

voyage/voyage-finance-2

Voyage Finance 2 is Voyage AI's finance-specialized embedding model with a context window of 0 tokens. It achieves 0.831 average NDCG@10 across 11 financial retrieval datasets, outperforming OpenAI text-embedding-3-large by 7% and Cohere Embed v3 by 12%.

index.ts
import { embed } from 'ai';


const result = await embed({
  model: 'voyage/voyage-finance-2',
  value: 'Sunny day at the beach',
})

What To Consider When Choosing a Provider

  • 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.

Voyage Finance 2 provides the largest accuracy gains on financial documents with hybrid tabular and textual content requiring numerical reasoning. If your financial data is primarily plain text without tables or numerical queries, a general-purpose model may perform comparably.

The context window of 0 tokens handles lengthy 10-K filings, research reports, and multi-page financial documents without truncation. This matters most for financial retrieval where key disclosures often appear late in long documents.

Voyage AI's voyage-3-large now outperforms domain-specific models on financial tasks. For new deployments with mixed financial and non-financial content, evaluate voyage-3-large or voyage-3.5 as simpler alternatives.

When to Use Voyage Finance 2

Best For

  • Financial document search:

    10-K filings, earnings reports, and SEC submissions where domain-specific terminology matters

  • RAG pipelines for financial analysis:

    Retrieval of relevant tables, figures, and text from company filings

  • Hybrid tabular-textual retrieval:

    Queries involve numerical reasoning over financial data alongside narrative content

  • Compliance and regulatory workflows:

    Search across financial regulations, guidance documents, and enforcement actions

  • Investment research:

    Pipelines that retrieve and rank relevant financial information from large document corpora

Consider Alternatives When

  • Your content spans multiple domains beyond finance:

    Voyage-3.5 or voyage-3-large provides cross-domain retrieval that includes finance

  • You want Matryoshka dimensionality and quantization:

    Voyage-3.5 offers these features while covering finance

  • Your financial data is primarily plain text without tables or numerical queries:

    A general-purpose model may perform comparably

  • You need code retrieval alongside financial data:

    Consider pairing with voyage-code-3 or using a general-purpose model

Conclusion

Voyage Finance 2 delivers measurable accuracy gains for financial document retrieval, particularly on hybrid tabular-textual datasets requiring numerical reasoning. Its context window of 0 tokens handles the lengthy documents common in finance without truncation. For pure financial retrieval workloads, it remains a specialized option. Access it through AI Gateway for unified provider management and usage tracking.

FAQ

Corporate event summaries, public company filings, 10-K reports, tabular financial data, personal finance content, and documents requiring numerical reasoning across tables and text.

Voyage Finance 2 outperforms OpenAI text-embedding-3-large by 7% and Cohere Embed v3 by 12% across 11 financial retrieval datasets, with an average NDCG@10 of 0.831.

Voyage AI's voyage-3-large now outperforms domain-specific models on financial benchmarks. For mixed financial and non-financial content, voyage-3-large or voyage-3.5 may be simpler. Use Voyage Finance 2 if your workload is exclusively financial and you have existing indices.

0 tokens. This handles lengthy financial filings and multi-page research reports without truncation, which is critical for documents where key disclosures appear deep in the text.

Yes. Voyage Finance 2 shows particular strength on benchmarks involving hybrid tabular and textual financial data (TAT-QA, ConvFinQA, FinQA), which test retrieval requiring numerical reasoning.

Add your Voyage AI API key in AI Gateway settings, then send embedding requests through AI Gateway. AI Gateway authenticates requests and records embedding usage.

11 financial retrieval datasets including TAT-QA (0.788 NDCG@10), ConvFinQA (0.820), and FinQA (0.795). These cover corporate filings, financial news, tabular data, and numerical reasoning tasks.