What is Voyage 2 API?
Voyage 2 is a general-purpose text embedding model for semantic search and similarity tasks.
Technical Specifications
- Supported inputs: Text
- Output: Embedding
- Context window: 4,000 tokens / Max output: —
- Endpoint: /embeddings
Performance Benchmarks
[embed]
Voyage 2 API Pricing
- Input: $0.13 / 1M tokens
Where to Use Voyage 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]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Semantic search over documentation, knowledge bases, or internal wikis is a documented use case for voyage-2, where it can retrieve relevant sections even when users phrase questions differently from the source text.
Retrieval-augmented generation (RAG) is another documented use case for voyage-2, using the model to retrieve relevant context from a large corpus before answer generation.
Clustering is also documented as a use case, including grouping similar content such as support tickets or feedback together.
Deduplication and similarity analysis are documented use cases as well, such as embedding support tickets to identify recurring issues.
import requests r = requests.post( "https://api.aimlapi.com/v1/embeddings", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "anthropic/voyage-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-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-2","input":"The quick brown fox"}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Voyage 2 This page | Semantic search + RAG | |||
| Semantic search + RAG | ||||
| Semantic search + RAG | ||||
| Semantic search + RAG |
Voyage 2 takes text as input and returns embedding.
Voyage 2 became available on December 13, 2025.
Voyage 2 is priced at input $0.13 / 1M tokens.
Voyage 2 was built by Anthropic.
Send a request to https://api.aimlapi.com/v1/embeddings with anthropic/voyage-2 as the model id.
Yes. Voyage 2 is served through AI/ML API, so the same key and endpoint format used for other models applies.
