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%.
import { embed } from 'ai';
const result = await embed({ model: 'voyage/voyage-finance-2', value: 'Sunny day at the beach',})Voyage Finance 2 is Voyage AI's finance-specialized embedding model, released March 1, 2024. It features a context window of 0 tokens and targets retrieval across financial documents including corporate event summaries, public company filings, 10-K reports, tabular financial data, personal finance content, and documents requiring numerical reasoning.
Across 11 financial retrieval datasets, Voyage Finance 2 achieves an average NDCG@10 of 0.831, outperforming OpenAI text-embedding-3-large by 7% and Cohere Embed v3 English by 12%. It shows particular strength on TAT-QA (0.788), ConvFinQA (0.820), and FinQA (0.795), which test retrieval over hybrid tabular and textual financial data requiring numerical understanding.
Voyage AI built Voyage Finance 2 for expertise-intensive domains where general-purpose embedding models underperform due to specialized terminology, document structures, and reasoning patterns unique to finance. The context window of 0 tokens handles lengthy financial filings and reports without truncation. That matters for 10-K documents and multi-page research reports where key information appears deep in the text.