Name: Voyage Large 2 API
Brand: Anthropic

Overview

What is Voyage Large 2 API?

Voyage Large 2 is a high-capacity embedding model offering strong performance across general-purpose retrieval tasks.

Technical Specifications
- Supported inputs: Text
- Output: Embedding
- Context window: 16,000 tokens / Max output: —
- Endpoint: /embeddings

Performance Benchmarks
[embed]

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

Where to Use Voyage Large 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

Text embeddings for general-purpose semantic retrieval and search are a direct use case for this model.

It can also be used to produce embeddings for document similarity and matching tasks, where text is encoded into vectors for comparing related content.

A further use case is retrieval-focused applications over large text collections, including search, indexing, and RAG-style document lookup.

How to use Voyage Large 2 API

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

import requests

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

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