Independent resource. Not affiliated with any provider. Always verify pricing on provider sites.
$embeddingcost

Voyage AI Embedding Pricing: voyage-4, voyage-4-large & voyage-4-lite (June 2026)

The voyage-4 family (January 2026) is Voyage's current generation and tops its own RTEB retrieval benchmark. Here is what it costs, when each tier is worth it, and the shared-vector-space feature that lets you mix models without re-indexing.

Verified June 2026 • 200M free tokens on the voyage-4 generation

How much does Voyage AI cost, and is there a free tier?

Voyage AI embeddings cost $0.02 per million tokens for voyage-4-lite, $0.06/M for voyage-4, and $0.12/M for voyage-4-large. Every account gets 200 million free tokens on the voyage-4 generation (about 400,000 documents at zero cost), and the Batch API takes 33% off every tier.

voyage-4-lite
$0.02/M
$0.013/M batch
voyage-4
$0.06/M
$0.04/M batch
voyage-4-large
$0.12/M
$0.08/M batch

All voyage-4 models share one vector space, so you can index with voyage-4-large and query with voyage-4-lite without re-indexing. The legacy voyage-3.x models no longer include the free allocation.

Current Pricing

Model$/M tokensBatch $/MDimsContextFree
voyage-4-large
Flagship (MoE)
$0.12$0.0801,02432,000200M
voyage-4
Recommended
$0.06$0.0401,02432,000200M
voyage-4-lite
Cost optimized
$0.02$0.0131,02432,000200M
voyage-code-3
Code search
$0.18$0.1201,02432,000200M
voyage-context-3
Contextual chunks
$0.18$0.1201,02432,000200M
voyage-law-2
Legal RAG
$0.12$0.0801,02416,00050M
voyage-finance-2
Financial RAG
$0.12$0.0801,02416,00050M

voyage-4 models default to 1024 dimensions with Matryoshka options (256/512/1024/2048). Batch jobs complete within 12 hours (33% off standard rate). Free column is the per-account lifetime allocation.

Why voyage-4 is the Price-Accuracy Sweet Spot

At $0.06/M tokens, voyage-4 costs 3x more than OpenAI text-embedding-3-small but approaches the retrieval quality of the previous flagship voyage-3-large at a mid-sized model's efficiency. For RAG applications where retrieval quality directly affects answer quality, that is a meaningful step up for English and multilingual content alike.

The top tier, voyage-4-large ($0.12/M), is the first production-grade embedding model to use a mixture-of-experts (MoE) architecture. On Voyage's RTEB benchmark (29 retrieval datasets across 8 domains) it outperforms OpenAI text-embedding-3-large by 14% and Cohere embed-v4 by 8.2% on NDCG@10, while MoE keeps serving costs roughly 40% below comparable dense models.

Use voyage-4 batch at $0.04/M for document indexing, and keep standard ($0.06/M) for real-time query embedding. At 1 billion indexing tokens + 10M monthly query tokens, your total monthly cost is $40 indexing (one-time) + $0.60 query = under $1/month ongoing after initial indexing.

The Shared-Vector-Space Feature

Built into voyage-4: All voyage-4 models (lite, 4, large) embed into the same vector space. You can index documents with voyage-4-large and query with voyage-4-lite without re-indexing.

Practical application: index your corpus once with voyage-4-large ($0.12/M, maximum quality) and serve real-time queries with voyage-4-lite ($0.02/M, fast). You pay the premium once for indexing, then query cheaply forever. For a 1B token corpus indexed once + 100M monthly query tokens: one-time index cost = $120, monthly query cost = $2.

Domain-Specific Models: When the Premium Pays

voyage-code-3
$0.18/M

Code search, documentation RAG, GitHub issue retrieval. Trained on code repositories.

Best for: Dev tools, documentation sites
voyage-law-2
$0.12/M

Legal document search, contract review. Trained on legal corpora with jurisdiction awareness.

Best for: Legal tech, compliance tools
voyage-finance-2
$0.12/M

Financial document retrieval, earnings call search, SEC filing analysis.

Best for: Fintech, financial analytics

Free Tier: 200M Lifetime Tokens on voyage-4

Every Voyage AI account receives 200 million free tokens on the voyage-4 generation (voyage-4-large, voyage-4, voyage-4-lite) plus voyage-context-3 and voyage-code-3, and 50 million free tokens on the voyage-2 domain models. At 500 tokens per document, 200M tokens is 400,000 documents you can embed at zero cost - enough to build and test an entire prototype RAG pipeline before spending anything. No card required. The older voyage-3.x models no longer include a free allocation.

Previous Generation: voyage-3.x

The voyage-3 series remains callable for existing indexes, with prices unchanged, but Voyage states the voyage-4 models are strictly better in quality, context length, latency, and throughput. The voyage-3.x models no longer include the 200M free allocation.

Legacy model$/M tokensDimsMTEB
voyage-3-large$0.182,04868.9
voyage-3.5$0.061,02467.1
voyage-3-lite$0.0251261.7

Frequently Asked Questions

How much does Voyage AI embedding cost?
voyage-4-lite: $0.02/M tokens. voyage-4: $0.06/M. voyage-4-large: $0.12/M. All voyage-4 models have a 33% batch discount and 200M free tokens.
What makes Voyage AI different from OpenAI embeddings?
voyage-4-large tops Voyage's RTEB benchmark, beating OpenAI text-embedding-3-large by 14% and Cohere embed-v4 by 8.2% on NDCG@10. Voyage also offers 32,000-token context windows vs OpenAI's 8,191, and domain-specific models for code, law, and finance.
What is the shared-vector-space feature in Voyage?
The voyage-4 models (lite, 4, large) all produce vectors in the same embedding space. You can index with voyage-4-large and query with voyage-4-lite without re-indexing.
Does Voyage AI have a free tier?
Yes. 200 million tokens free on the voyage-4 generation plus voyage-context-3 and voyage-code-3, and 50 million on the voyage-2 domain models. The older voyage-3.x models no longer include a free allocation.
What is the Voyage AI batch API discount?
33% off standard rates. voyage-4 drops from $0.06/M to $0.04/M. Batch jobs complete within 12 hours.
Should I use voyage-4 or the older voyage-3.5?
Use voyage-4 - the January 2026 generation that Voyage states is strictly better than voyage-3 in quality, context, latency, and throughput. voyage-3.x remains callable for existing indexes but has no free allocation.
Compare all models
Voyage vs OpenAI vs Cohere vs Google
Full calculator
See Voyage cost with storage included
RAG scenarios
Real workload cost examples with Voyage
Disclaimer: Independent resource. Not affiliated with Voyage AI. Pricing from Voyage AI's public pricing page, verified June 2026. Verify at docs.voyageai.com.

Updated June 2026