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.
Current Pricing
| Model | $/M tokens | Batch $/M | Dims | Context | MTEB |
|---|---|---|---|---|---|
voyage-3.5 Recommended | $0.06 | $0.040 | 1,024 | 32,000 | 67.1 |
voyage-3-large Max accuracy | $0.18 | $0.120 | 2,048 | 32,000 | 68.9 |
voyage-3-lite Cost optimized | $0.02 | $0.013 | 512 | 32,000 | 61.7 |
voyage-code-3 Code search | $0.06 | $0.040 | 1,024 | 32,000 | N/A |
voyage-law-2 Legal RAG | $0.12 | $0.080 | 1,024 | 16,000 | N/A |
voyage-finance-2 Financial RAG | $0.12 | $0.080 | 1,024 | 16,000 | N/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
Code search, documentation RAG, GitHub issue retrieval. Trained on code repositories.
Legal document search, contract review. Trained on legal corpora with jurisdiction awareness.
Financial document retrieval, earnings call search, SEC filing analysis.
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.