Voyage: Voyage 3 Large

Voyage 3 Large is an earlier-generation embedding model for general-purpose and multilingual retrieval. It remains useful for applications maintaining an existing Voyage 3 Large vector index; switching embedding generations should include reindexing and retrieval evaluation.

Compare models

voyage-3-large

AvailableVoyageEmbeddingSync

Input / Output: $0.18 / $0.00
Context: 32K
Modalities: Embedding

About Voyage 3 Large

Voyage 3 Large is Voyage AI's earlier-generation text embedding model for general-purpose and multilingual retrieval. Voyage identifies Voyage 4 Large as its replacement. It is mainly relevant for applications that keep a Voyage 3 Large vector index and want to postpone re-embedding until a retrieval evaluation justifies the move.

Where it works well

It covers general-purpose and multilingual retrieval for search and RAG.
Existing Voyage 3 Large indexes can keep running without changes.
Dimensions of 256, 512, 1024, and 2048 can be requested.
Quantized outputs include int8, uint8, binary, and ubinary.

When to choose another model

Voyage 4 Large replaces it, so a new index should begin there.
Series 4 models cannot query its vectors, because the two generations use separate spaces.

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-3-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 $0.18 / Output $0.00
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Embedding	Input $0.18 / 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 3 Large in Console with a prompt ready to edit or send.

Help me try voyage-3-large with embedding at /v1/embeddings. Show the result and cost.

Use cases

Maintaining a legacy index
Add new documents to an archive that was embedded with this model, keeping every vector in one space.
Re-indexing benchmark
Use it as the baseline when you test whether Voyage 4 Large improves recall on your corpus.
Storage-reduced search
Request binary output to hold a large collection of vectors in far less space.

Prompt examples

Embed this legal summary as a document for the research archive.

Embed the query: causes of the 2008 liquidity crisis.

Embed the query in Portuguese: política de privacidade de dados.

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

Is Voyage 3 Large still recommended?

Not for new work. Voyage lists it as a previous-generation model and names Voyage 4 Large as the replacement. Keep it only while an existing index depends on it, and schedule a re-embedding with retrieval testing.

Can I query a Voyage 3 Large index with Voyage 4 Large?

No. Compatibility is documented inside Series 4 only. Re-embed the entire corpus with Voyage 4 Large, then compare retrieval results against the old index before cutting over.

What dimensions and output types are available?

Dimensions 256, 512, 1024 (default), and 2048, plus int8, uint8, binary, and ubinary outputs. Choose once per index, because every vector in an index must use the same setting.

How is it different from Voyage 3.5?

Voyage 3 Large is the larger, quality-oriented model of the Series 3 line, while Voyage 3.5 is the later general-purpose release. Both are previous generation, and neither mixes with Series 4 vectors.

How much does Voyage 3 Large cost?

On TokenLab, Voyage 3 Large costs Input $0.18 / 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 3 Large use?

Use https://api.tokenlab.sh/v1/embeddings for Voyage 3 Large. The request example below shows the matching code shape.

Which operations does Voyage 3 Large support?

Voyage 3 Large supports Embedding. Select an operation above to see its endpoint and request example.