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

Voyage AI Embedding Pricing: voyage-3.5, voyage-3-large & voyage-3-lite (May 2026)

Voyage leads the MTEB leaderboard. Here is what it costs, when it is worth the premium, and the unique same-vector-space feature that no other provider offers.

Verified May 2026 • 200M free tokens on all accounts

Current Pricing

Model$/M tokensBatch $/MDimsContextMTEB
voyage-3.5
Recommended
$0.06$0.0401,02432,00067.1
voyage-3-large
Max accuracy
$0.18$0.1202,04832,00068.9
voyage-3-lite
Cost optimized
$0.02$0.01351232,00061.7
voyage-code-3
Code search
$0.06$0.0401,02432,000N/A
voyage-law-2
Legal RAG
$0.12$0.0801,02416,000N/A
voyage-finance-2
Financial RAG
$0.12$0.0801,02416,000N/A

All Voyage AI accounts receive 200M free lifetime tokens. Batch jobs complete within 12 hours (33% off standard rate).

Why voyage-3.5 is the Price-Accuracy Sweet Spot

At $0.06/M tokens, voyage-3.5 costs 3x more than OpenAI text-embedding-3-small but delivers a 4.8-point MTEB Retrieval improvement (67.1 vs 62.3). For RAG applications where retrieval quality directly affects answer quality, this is a meaningful difference - roughly 5-8% better precision at top-5 recall for technical and domain-specific content.

Use voyage-3.5 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 Same-Vector-Space Feature

Unique to Voyage: All voyage-3 models (lite, 3.5, large) embed into the same vector space. You can index documents with voyage-3-large and query with voyage-3-lite without re-indexing.

Practical application: index your corpus once with voyage-3-large ($0.18/M, maximum quality) and serve real-time queries with voyage-3-lite ($0.02/M, 512 dims, 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 = $180, monthly query cost = $2.

Domain-Specific Models: When the Premium Pays

voyage-code-3
$0.06/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

Every Voyage AI account receives 200 million free tokens shared across all models. At 500 tokens per document, that is 400,000 documents you can embed at zero cost. For a typical prototype RAG application (10k-50k documents), you can build and test the entire embedding pipeline before spending anything. No card required for the free tier.

Frequently Asked Questions

How much does Voyage AI embedding cost?
voyage-3-lite: $0.02/M tokens. voyage-3.5: $0.06/M. voyage-3-large: $0.18/M. All models have 33% batch discounts and 200M free tokens for life.
What makes Voyage AI different from OpenAI embeddings?
Voyage consistently ranks near the top of the MTEB Retrieval leaderboard. voyage-3.5 scores 67.1 MTEB vs OpenAI small at 62.3. 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 same-vector-space feature in Voyage?
Voyage-3 models (lite, 3.5, large) all produce vectors in the same embedding space. You can index with voyage-3-large and query with voyage-3-lite without re-indexing - unique flexibility no other provider offers.
Does Voyage AI have a free tier?
Yes. All accounts receive 200 million tokens free for life across all Voyage models. At 500 tokens per document, that is 400,000 free document embeddings.
What is the Voyage AI batch API discount?
33% off standard rates. voyage-3.5 drops from $0.06/M to $0.04/M. Batch jobs complete within 12 hours.
When should I use voyage-3-lite vs voyage-3.5 vs voyage-3-large?
voyage-3-lite for high-volume query embedding where cost matters most. voyage-3.5 for document indexing - best accuracy-to-cost ratio. voyage-3-large when maximum retrieval quality is worth the 3x premium over voyage-3.5.
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 May 2026. Verify at docs.voyageai.com.

Updated May 2026