Voyage: Voyage Law 2

Voyage Law 2 specializes in retrieval over legal text. Its embeddings support searching legal documents and assembling relevant context from contracts, legislation, and case materials for a downstream application.

Compare models

voyage-law-2

AvailableVoyageEmbeddingSync

Input / Output: $0.12 / $0.00
Context: 16K
Modalities: Embedding

About Voyage Law 2

Voyage Law 2 is a Voyage AI embedding model optimized for legal retrieval and retrieval-augmented generation. It supports searching contracts, legislation, and case materials, and assembling relevant context for a downstream application. Vectors are 1024-dimensional, and its input limit is half that of the Series 4 models, so long legal documents need to be split into sections.

Where it works well

Voyage optimizes it for legal retrieval and RAG.
It targets contracts, legislation, and case materials, where wording matters to relevance.
Each embedding has 1024 dimensions, which fixes the storage per vector.
It works with the standard embed-then-search pipeline using query and document input types.

When to choose another model

Its input limit is shorter than the Series 4 models, so long documents must be chunked more finely.
As a legal specialist, it may trail Voyage 4 Large on mixed-topic corpora; check on your own data.

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-law-2",
  "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 Law 2 in Console with a prompt ready to edit or send.

Help me try voyage-law-2 with embedding at /v1/embeddings. Show the result and cost.

Use cases

Clause search
Embed contract sections so a reviewer can find every termination, indemnity, or liability clause across a repository.
Case-law research
Search past decisions for passages matching a fact pattern described in plain language.
Legal assistant grounding
Retrieve statute or contract passages for a chat model to cite when answering a counsel's question.

Prompt examples

Embed the query: clauses allowing unilateral termination without cause.

Embed this indemnification section as a document for the contract index.

Embed the query: precedent on limitation of liability for data breaches.

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

What is Voyage Law 2 for?

Legal retrieval and RAG, according to Voyage. It embeds legal text so contracts, legislation, and case materials can be searched by meaning, and so relevant passages can be handed to a language model as context.

How long can an input to Voyage Law 2 be?

Voyage lists a context half the size of the Series 4 limit for this model. Split long agreements by section or clause before embedding; clause-level chunks also give more precise search results.

Should I pick Voyage Law 2 or Voyage 4 Large for legal documents?

Try both on a sample of your real questions. Voyage Law 2 is trained for legal text, while Voyage 4 Large is the general-purpose quality leader of the current series and offers flexible dimensions.

Which dimension does Voyage Law 2 return?

Voyage's documentation lists 1024 dimensions. Queries and documents must both be embedded with this model, since its vectors do not mix with other Voyage models.

How much does Voyage Law 2 cost?

On TokenLab, Voyage Law 2 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 Law 2 use?

Use https://api.tokenlab.sh/v1/embeddings for Voyage Law 2. The request example below shows the matching code shape.

Which operations does Voyage Law 2 support?

Voyage Law 2 supports Embedding. Select an operation above to see its endpoint and request example.