Voyage: Voyage Finance 2

Voyage Finance 2 specializes in financial text retrieval and retrieval-augmented generation. It can index material such as financial reports and disclosures so that applications retrieve relevant passages before generating an answer.

Compare models

voyage-finance-2

AvailableVoyageEmbeddingSync

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

About Voyage Finance 2

Voyage Finance 2 is a Voyage AI embedding model optimized for finance retrieval and retrieval-augmented generation. It indexes material such as annual reports, filings, and disclosures so an application can pull the relevant passages before a language model answers. Vectors are 1024-dimensional, and the model is domain-specific, unlike the general Voyage 4 family.

Where it works well

Voyage optimizes it for finance retrieval and RAG rather than general text.
It suits reports, filings, and disclosures where financial terminology drives relevance.
Vectors are 1024-dimensional, so the index size is predictable.
It slots into a standard embed-then-search pipeline with query and document input types.

When to choose another model

It is specialized for finance, so mixed-domain corpora may retrieve better with Voyage 4 or Voyage 4 Large.
Voyage's documentation lists a single 1024 dimension, without the flexible sizes of Series 4.

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-finance-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 Finance 2 in Console with a prompt ready to edit or send.

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

Use cases

Filing and report search
Embed annual reports and regulatory filings so analysts can find the passages relevant to a specific risk or metric.
Grounding finance chatbots
Retrieve disclosure passages for a model to quote when answering questions about a company.
Earnings call lookup
Search earnings call transcripts for statements about guidance, margins, or capital plans.

Prompt examples

Embed the query: what drove the decline in net interest margin?

Embed this risk-factors section of a 10-K as a document.

Embed the query: covenant breaches disclosed in the last two filings.

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 Finance 2 designed for?

Finance retrieval and RAG, as Voyage puts it. It embeds financial text such as reports and disclosures so an application retrieves the right passages before generating an answer, instead of relying on general-purpose vectors.

When should I use a general Voyage model instead?

When your corpus mixes finance with other topics, or when you want adjustable dimensions. Voyage 4 and Voyage 4 Large cover general and multilingual retrieval. Test both on your own questions, since domain tuning helps only on matching text.

What dimension does Voyage Finance 2 return?

Voyage's documentation lists 1024 dimensions, with no alternative sizes. Plan your vector store for that size, and keep queries and documents on the same model.

Can I mix its vectors with Series 4 vectors?

No. Voyage documents compatibility among Series 4 models only. A finance index built with this model should be searched with query vectors from the same model.

How much does Voyage Finance 2 cost?

On TokenLab, Voyage Finance 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 Finance 2 use?

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

Which operations does Voyage Finance 2 support?

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