Voyage AI Embedding Pricing: voyage-4, voyage-4-large & voyage-4-lite (September 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.
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.
One catch worth knowing before you plan a build: the free tokens do not apply to the Batch API. Voyage bills every batch token at the discounted rate and does not deduct it from your free balance, so inside the first 200M tokens the standard API is free and batch is not.
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. Prices, free allocations and the batch rule verified at docs.voyageai.com/docs/pricing on 16 September 2026.
Current Pricing
| Model | $/M tokens | Batch $/M | Dims | Context | Free |
|---|---|---|---|---|---|
voyage-4-large Flagship (MoE) | $0.12 | $0.080 | 1,024 | 32,000 | 200M |
voyage-4 Recommended | $0.06 | $0.040 | 1,024 | 32,000 | 200M |
voyage-4-lite Cost optimized | $0.02 | $0.013 | 1,024 | 32,000 | 200M |
voyage-code-4 Code search | $0.12 | $0.080 | 1,024 | 32,000 | 200M |
voyage-context-4 Contextual chunks | $0.12 | $0.080 | 1,024 | 32,000 | 200M |
voyage-law-2 Legal RAG | $0.12 | $0.080 | 1,024 | 16,000 | 50M |
voyage-finance-2 Financial RAG | $0.12 | $0.080 | 1,024 | 32,000 | 50M |
voyage-code-2 Legacy code model | $0.12 | $0.080 | 1,024 | not listed | 50M |
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
Code search, documentation RAG, GitHub issue retrieval. Replaced voyage-code-3, which sat at $0.18/M and is now a legacy model.
Legal document search, contract review. Trained on legal corpora with jurisdiction awareness.
Financial document retrieval, earnings call search, SEC filing analysis.
Free Tier: 200M Free Tokens, and the Batch Rule That Cancels Them
The free tier is 200 million tokens per account, and it does not apply to the Batch API. Voyage's pricing page states it plainly: "Free token credits do not apply to Batch API usage. All successfully processed Batch API tokens are billed at the applicable discounted batch rate and do not deduct from your free token balance." So the standard-rate and batch-rate paths are mutually exclusive while you are inside the allocation. Index through the standard API and the first 200M tokens cost nothing. Index through the Batch API and you pay the 33% discounted rate from token one.
The practical consequence: for a first corpus under 200M tokens, the standard API is free and the Batch API is not. At 200M tokens, standard costs $0 and batch voyage-4 costs $8.00. The batch discount only starts saving money once the free balance is spent. Above that line the ranking flips, and batch at $0.04/M beats standard at $0.06/M on every token.
The 200M allocation covers voyage-4-large, voyage-4, voyage-4-lite, voyage-context-4 and voyage-code-4. The 50M allocation covers voyage-multilingual-2, voyage-finance-2, voyage-law-2 and voyage-code-2. The rerank-3 models carry their own 200M allocation; rerank-2.5 and rerank-2.5-lite carry none. At 500 tokens per document, 200M tokens is 400,000 documents at zero cost, enough to build and test a prototype RAG pipeline before spending anything. No card required. The older voyage-3.x models no longer include a free allocation.
Source: docs.voyageai.com/docs/pricing, verified 16 September 2026.
Rerankers and Multimodal: The Rest of the Published Price List
Voyage publishes prices for two product lines beyond text embeddings. Rerankers are priced per million tokens like embeddings, and the multimodal embedders are priced per million text tokens with a separate free pixel allowance. All carry the same 33% batch discount.
| Model | Price | Free allocation | Notes |
|---|---|---|---|
| rerank-3 | $0.05/M | 200M | Current reranker |
| rerank-3-lite | $0.02/M | 200M | Cost-optimised reranker |
| rerank-2.5 | $0.05/M | None | Previous reranker, no free allocation |
| rerank-2.5-lite | $0.02/M | None | Previous lite reranker, no free allocation |
| voyage-multimodal-3.5 | $0.12/M | 200M tokens + 150B pixels | Text and image in one space |
| voyage-multimodal-3 | $0.12/M | 200M tokens + 150B pixels | Previous multimodal model |
Source: docs.voyageai.com/docs/pricing, verified 7 September 2026. voyage-code-3 now sits in Voyage's older-models table at $0.18/M; voyage-code-4 at $0.12/M is the current code model.
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 tokens | Dims | MTEB |
|---|---|---|---|
| voyage-3-large | $0.18 | 2,048 | 68.9 |
| voyage-3.5 | $0.06 | 1,024 | 67.1 |
| voyage-3-lite | $0.02 | 512 | 61.7 |