Name: Voyage finance 2 API
Brand: Anthropic

Overview

What is Voyage finance 2 API?

Voyage Finance 2 is a domain-specific embedding model optimized for financial text retrieval and semantic search.

Technical Specifications
- Supported inputs: Text
- Output: Embedding
- Context window: 32,000 tokens / Max output: —
- Endpoint: /embeddings

Performance Benchmarks
[embed]

Voyage finance 2 API Pricing
- Input: $0.156 / 1M tokens

Where to Use Voyage finance 2

Semantic search
Rank documents by meaning for retrieval and discovery.

RAG pipelines
Ground LLM answers in your own data via vector retrieval.

Code Sample
[embed]

Use cases

Voyage finance 2 is suited for financial document search, including 10-K filings, earnings reports, and SEC submissions where domain-specific terminology matters. It is also documented for retrieval in RAG pipelines for financial analysis, where relevant tables, figures, and text are pulled from company filings.

It is suited for hybrid tabular-textual retrieval, including queries that involve numerical reasoning over financial data alongside narrative content. It is also documented for compliance and regulatory workflows, such as searching financial regulations, guidance documents, and enforcement actions.

How to use Voyage finance 2 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/voyage-finance-2.

import requests

r = requests.post(
    "https://api.aimlapi.com/v1/embeddings",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/voyage-finance-2",
      "input": "The quick brown fox"
    },
)
print(r.json())

const r = await fetch("https://api.aimlapi.com/v1/embeddings", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthropic/voyage-finance-2",
    "input": "The quick brown fox"
  }),
});
console.log(await r.json());

curl -X POST https://api.aimlapi.com/v1/embeddings \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/voyage-finance-2","input":"The quick brown fox"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.