All models
Voyage AI
Voyage 4 Large
Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space.
Plain-English overview
What Voyage 4 Large actually is
Voyage 4 Large turns text or code into vectors for semantic search and RAG. It is the quality-focused member of the Voyage 4 family, while smaller siblings can be used when cost or latency matters more.
Models in the family share a compatible vector space. That can let a team index documents with a higher-quality model and use a lighter compatible model for some queries, although the exact routing design still needs workload-specific evaluation.
Good fit for
- Quality-sensitive text retrieval
- Search that mixes prose and code
- Teams evaluating asymmetric index and query models
Category comparison
The facts that matter for embeddings models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Embedding price
- $0.12 / 1M tokens after 200M freeCurrent provider price per million input tokens or the closest published billing unit.
- Input capacity
- 32K tokensMaximum content accepted in one embedding input, using the provider's documented token basis.
- Vector dimensions
- 1,024 default; 256, 512, or 2,048 optionalSupported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
- Accepted inputs
- Text and codeText, code, image, audio, video, PDF, or document-aware input supported by the endpoint.
- Retrieval controls
- Query/document input types, truncation, output dimensionQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval.
- Where it runs
- Voyage API, MongoDB Atlas, and selected cloudsDirect API, cloud marketplace, private deployment, or self-hosted route documented by the provider.
Quality and speed evidence
Results describe a specific test, language and configuration—not overall intelligence. Missing results do not imply worse quality.
Voyage 4 Large · FinanceBenchRetrieval
Community-submitted result
Retrieval relevance (0–1; higher is better)
Test configuration
MTEB · 2.1.3 · eng-Latn · test/default
dimensions: 1024 · similarity: cosine · modelMetadata: https://github.com/embeddings-benchmark/results/blob/main/results/voyageai__voyage-4-large/1/model_meta.json
Checked: September 5, 2026
MTEB contributors · FinanceBenchRetrieval0.9288 nDCG@10
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Assumes 600 tokens per page, processed separately. Actual token counts vary. This covers embedding only, not storage, search, or generated answers.
Voyage 4 Large
Voyage AI
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
- Input tokens
- $0.12 per 1M tokens
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Voyage 4 Large
Availability
Regions and access stage
Available through the Voyage API and selected MongoDB and cloud-platform routes.
The reviewed public docs do not enumerate a single processing-country list; cloud and enterprise routes depend on the chosen deployment.
Check live availabilityData and training
The route matters.
Voyage's public terms allow customer content to improve services unless the customer opts out. Eligible paid organizations can configure an opt-out and zero-day retention; separately negotiated enterprise terms may differ.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Voyage 4 Large FAQ
What is Voyage 4 Large?
Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space. Voyage 4 Large turns text or code into vectors for semantic search and RAG. It is the quality-focused member of the Voyage 4 family, while smaller siblings can be used when cost or latency matters more.
When was Voyage 4 Large released?
Voyage 4 Large was released on January 15, 2026 according to the cited provider materials.
Where can I access Voyage 4 Large?
Available through the Voyage API and selected MongoDB and cloud-platform routes. The access routes listed in this guide are Voyage AI and MongoDB Atlas.
How much does Voyage 4 Large cost?
$0.12 / 1M tokens after 200M free. Voyage lists a 200-million-token free allowance and a lower batch rate. Confirm current account eligibility and overage pricing before forecasting.
Where is Voyage 4 Large available?
Available through the Voyage API and selected MongoDB and cloud-platform routes. The reviewed public docs do not enumerate a single processing-country list; cloud and enterprise routes depend on the chosen deployment.
Is my Voyage 4 Large API data used for training?
Voyage's public terms allow customer content to improve services unless the customer opts out. Eligible paid organizations can configure an opt-out and zero-day retention; separately negotiated enterprise terms may differ. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Embed$0.10
Mistral AI
- Voyage 4 Large$0.12
Voyage AI
This model
- Voyage Context 4$0.12
Voyage AI
- Voyage Code 4$0.12
Voyage AI
- text-embedding-3-large$0.13
OpenAI
- Gemini Embedding 2$0.20
Google
Related comparisons
Head-to-head comparisons
Voyage 4 Large vs Gemini Embedding 2
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.
Open full comparisonVoyage 4 Large vs text-embedding-3-large
OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.
Open full comparisonVoyage 4 Large vs Cohere Embed 4
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
Open full comparisonVoyage 4 Large vs Voyage Context 4
Voyage AI's document-aware embedding model that automatically creates vectors for chunks while preserving information from the surrounding document.
Open full comparisonVoyage 4 Large vs Voyage Code 4
Voyage AI's specialist embedding model for finding relevant code from natural-language questions or other source-code context.
Open full comparisonVoyage 4 Large vs Mistral Embed
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.
Open full comparison
