Voyage: Voyage 4 Large

Voyage 4 Large is the larger model in Voyage's fourth-generation multilingual retrieval family. Its vectors share an embedding space with Voyage 4 and Voyage 4 Lite, so applications can use different family members for document indexing and query embedding.

Compare models

voyage-4-large

AvailableVoyageEmbeddingSync

Input / Output: $0.12 / $0.00
Context: 32K
Modalities: Embedding

About Voyage 4 Large

Voyage 4 Large is the top model of Voyage AI's fourth embedding series, which Voyage describes as having the best general-purpose and multilingual retrieval quality. Its vectors share one space with Voyage 4 and Voyage 4 Lite, so a team can index documents with the large model and embed live queries with a smaller one. Dimensions default to 1024.

Where it works well

Voyage ranks it as the highest-quality general and multilingual retriever of Series 4.
Document indexes built with it can be queried with Voyage 4 or Voyage 4 Lite vectors.
Four output dimensions are offered, from 256 to 2048.
It replaces Voyage 3 Large as the recommended upgrade.

When to choose another model

It is the heaviest Series 4 model, so high-volume or latency-sensitive query embedding is better served by Voyage 4 Lite.
It handles text only; code retrieval is the job of Voyage Code 3.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

EmbeddingTokenLab endpoint

POST/v1/embeddings

curl -X POST "https://api.tokenlab.sh/v1/embeddings" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "encoding_format": "float",
  "model": "voyage-4-large",
  "input": "The quick brown fox jumps over the lazy dog."
}'

Parameters

Embedding

Parameter	Values and limits	Default	Notes
`encoding_format`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`input`	Inputs: ≥ 1, ≤ 1000	Not provided	Not provided

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Embedding

per 1M tokens

Official price: Input $0.12 / Output $0.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Embedding	Input $0.12 / Output $0.00	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 15, 2026, 1:51 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Voyage 4 Large in Console with a prompt ready to edit or send.

Help me try voyage-4-large with embedding at /v1/embeddings. Show the result and cost.

Use cases

High-recall enterprise search
Embed a large archive once with the strongest model so every later search draws on the best vectors available.
Asymmetric retrieval
Index documents with this model and embed user queries with Voyage 4 Lite to keep query latency low.
Replacing Voyage 3 Large
Move an existing index to the current generation after re-embedding and checking recall on your own queries.

Prompt examples

Embed this 20-page policy document in sections for the compliance search index.

Embed the query: which suppliers failed the 2025 audit?

Embed this Japanese product FAQ entry as a document.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

When should I pick Voyage 4 Large over Voyage 4?

Pick it when retrieval quality matters more than throughput, such as a one-time indexing of a valuable corpus. Voyage lists it as the best-quality model in Series 4. Voyage 4 is the balanced choice for everyday workloads.

Can I mix Voyage 4 Large with smaller Series 4 models?

Yes. Series 4 embeddings are mutually compatible, so you can embed documents with Large and queries with Voyage 4 or Voyage 4 Lite. This keeps index quality high while reducing the work done at query time.

Does Voyage 4 Large replace Voyage 3 Large?

Voyage names it as the replacement for Voyage 3 Large. The two do not share a vector space, so switching means re-embedding the whole corpus and re-checking retrieval results first.

Which dimensions can Voyage 4 Large return?

1024 by default, plus 256, 512, and 2048. Pick one dimension per index and use it for every vector in that index, both documents and queries.

How much does Voyage 4 Large cost?

On TokenLab, Voyage 4 Large costs Input $0.12 / Output $0.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Voyage 4 Large use?

Use https://api.tokenlab.sh/v1/embeddings for Voyage 4 Large. The request example below shows the matching code shape.

Which operations does Voyage 4 Large support?

Voyage 4 Large supports Embedding. Select an operation above to see its endpoint and request example.