Voyage 3 Large Pricing
Voyage 3 Large is an embedding model from Voyage AI, priced at $0.1800 per 1M tokens. It produces 2048-dimensional vectors and accepts inputs up to 32,000 tokens.
Prices verified against official pricing pages. Sources: Voyage AI
Legacy model. Voyage lists the voyage-3 family as older models with no free-token allowance. Newer option: voyage-4-large at $0.12 per 1M tokens.
What does it cost to embed a corpus with Voyage 3 Large?
Embedding cost is a one-time charge per document — unlike LLM inference, you only pay to embed each chunk once at ingest time. Re-embedding only happens when you re-chunk or swap models.
| Corpus size | Tokens | One-time embed cost |
|---|---|---|
| Small docs corpus (~1M tokens) | 1,000,000 | $0.1800 |
| Mid-size corpus (~50M tokens) | 50,000,000 | $9.0000 |
| Enterprise corpus (~500M tokens) | 500,000,000 | $90.0000 |
Want to model your RAG stack end-to-end? RAG cost calculator →
Vector database sizing — what 2048-dim vectors cost to store
Each Voyage 3 Large embedding is a 2048-dimensional float32 vector, ~ 8.00 KB per vector. At 1M vectors that's ~ 7812.5 MB of raw vector data (before index overhead). Compare against alternates with different dimension counts:
- OpenAI text-embedding-3-small: 1536 dims → 5859.4 MB per 1M vectors
- OpenAI text-embedding-3-large: 3072 dims → 11718.8 MB per 1M vectors
- Voyage 3 Large: 2048 dims → 7812.5 MB per 1M vectors
- Voyage 3 Lite: 512 dims → 1953.1 MB per 1M vectors
- Cohere Embed v4: 1024 dims → 3906.3 MB per 1M vectors
- Gemini Embedding: 768 dims → 2929.7 MB per 1M vectors
Alternatives to Voyage 3 Large
Cheaper embedding models
Other Voyage AI embedding models: Voyage 3 Lite
FAQ
How much does Voyage 3 Large cost?
Voyage 3 Large costs $0.1800 per 1M tokens.
What are Voyage 3 Large's embedding dimensions?
Voyage 3 Large outputs 2048-dimensional vectors. This affects both storage size and similarity computation speed in your vector database.
What is the max input length?
Voyage 3 Large accepts inputs up to 32,000 tokens. Larger documents must be chunked before embedding.
What's the cheapest alternative?
The cheapest comparable model is OpenAI text-embedding-3-small at $0.0200 per 1M tokens.