# Voyage 4 Large

The Voyage 4 flagship built on a mixture-of-experts (MoE) architecture. Voyage 4 Large leads the series in retrieval accuracy while Voyage AI by MongoDB reports serving costs roughly 40% below comparable dense models.

- **Model ID:** `voyage/voyage-4-large`
- **Type:** embedding
- **Providers:** voyage
- **Context window:** 32,000
- **Maximum output tokens:** 0
- **Pricing:** $0.12/1M input tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/voyage-4-large

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { embed } from 'ai';

const result = await embed({
  model: 'voyage/voyage-4-large',
  value: 'Sunny day at the beach',
})
```

## About

Voyage 4 Large is the first production embedding model to use a mixture-of-experts architecture, released January 15, 2026. MoE activates only a subset of parameters per token, achieving flagship-level retrieval accuracy at lower inference cost than a dense model of equivalent quality.

Voyage AI by MongoDB reports Voyage 4 Large surpasses voyage-3-large on retrieval accuracy at a lower price point, with serving costs about 40% below comparable dense models. It supports a context window of 32K tokens and the full Matryoshka dimension set (2048, 1024, 512, 256) with quantization-aware training.

As the top of the Voyage 4 series, Voyage 4 Large produces the strongest average retrieval scores in Voyage AI by MongoDB's published benchmarks. Use it for document embeddings in asymmetric setups where you pair it with `voyage-4` or `voyage-4-lite` on the query side to control per-query costs.

## What to consider

Voyage 4 Large targets teams that need top published scores and can pay for the flagship on the paths that matter (often document embedding).

Pair Voyage 4 Large document vectors with smaller Voyage 4 query models when query volume is high.

Treat a move to Voyage 4 as a new index. Test on a sample corpus before you re-embed everything.

## When to use

### Best For

- **Corpus embedding** when you want flagship document vectors in Voyage AI by MongoDB's published Voyage 4 results
- **Asymmetric RAG** with smaller Voyage 4 query models
- **Long documents** within the window of 32K tokens
- **Migration from voyage-3-large** with a planned full re-embed into Voyage 4

### Consider Alternatives When

- **You need lower query cost**; use `voyage-4-lite` for queries, or `voyage-4` for balanced symmetric use
- **You need mid-tier only**; use `voyage-4`
- **Code-only corpora**; use `voyage-code-3`
- **Multimodal embeddings**; use a model with native image inputs

## Best for

- **Corpus embedding once:** You want maximum document-side quality in Voyage AI by MongoDB's published Voyage 4 results
- **Asymmetric RAG:** Documents use Voyage 4 Large and queries use `voyage-4-lite`
- **Enterprise search:** Long documents within the window of 32K tokens
- **Upgrades from voyage-3-large:** You accept a full re-embed for Voyage 4's shared space and MoE gains

## Consider alternatives

- **Lower per-query cost:** Use `voyage-4` or `voyage-4-lite` for queries, or symmetric indexing with a smaller Voyage 4 model
- **Mid-tier symmetric use:** `voyage-4` when you want one model for both sides
- **Code-only corpora:** Use `voyage-code-3` for repositories where source code is the primary content type
- **Multimodal embeddings:** Pick a model with native image inputs

## Frequently asked questions

### What is the difference between Voyage 4 Large and voyage-4?

Voyage 4 Large is the MoE flagship with the highest average scores in Voyage AI by MongoDB's published Voyage 4 comparison. `voyage-4` is the mid-sized model. Both share the same embedding space as `voyage-4-lite`.

### How does Voyage 4 Large compare to voyage-3-large?

Voyage AI by MongoDB reports better retrieval accuracy than voyage-3-large at a lower price, using MoE and the Voyage 4 training stack. Moving from Voyage 3 to Voyage 4 requires re-embedding because the embedding space changes.

### What is the context window for Voyage 4 Large?

32K tokens. Size chunks so single requests stay under this limit on long documents.

### When should I use Voyage 4 Large over voyage-4-lite?

Use Voyage 4 Large when you need the strongest published Voyage 4 vectors, especially for one-time or infrequent document embedding. Use `voyage-4-lite` when you want fewer parameters for queries or symmetric indexing at lower compute.

### How do I access Voyage 4 Large through Vercel AI Gateway?

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

### Do I need to re-embed my data to switch from voyage-3-large?

Yes. Moving from Voyage 3 to Voyage 4 requires re-embedding because the embedding space is new. Within Voyage 4, you can often keep `voyage-4-large` document vectors and change query models if you use asymmetric retrieval.

### Is Voyage 4 Large suitable for RAG applications?

Yes. Voyage AI by MongoDB positions it for retrieval-augmented generation and high-accuracy document indexing, including asymmetric setups where queries use a smaller Voyage 4 model.

### What is mixture-of-experts in Voyage 4 Large?

Voyage 4 Large routes tokens through expert subnetworks so Voyage AI by MongoDB can raise accuracy while reporting serving costs about 40% lower than comparable dense models.

## Links

- [Model page](https://vercel.com/ai-gateway/models/voyage-4-large)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://docs.voyageai.com/docs/embeddings)
- [Provider pricing](https://docs.voyageai.com/docs/pricing)