Model comparison
Compare Cohere Embed 4 and Voyage 4 Large using the same provider-sourced embeddings & vector search rubric. No mystery score and no invented benchmark ranking.
Facts checked September 4, 2026
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.
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.
| Model | Access | Estimated total (USD) |
|---|---|---|
| Voyage 4 LargeVoyage AI | Voyage AI | $0.0007 |
| Cohere Embed 4Cohere | Cohere | No reviewed rate |
Results describe a specific test, language and configuration—not overall intelligence. Missing results do not imply worse quality.
These results use different test settings and are not a like-for-like ranking.
Community-submitted result
Retrieval relevance (0–1; higher is better)
MTEB · 1.38.43 · eng-Latn · test/default
dimensions: 1536 · similarity: cosine · modelMetadata: https://github.com/embeddings-benchmark/results/blob/main/results/Cohere__Cohere-embed-v4.0/1/model_meta.json
Checked: September 5, 2026
MTEB contributors · FinanceBenchRetrieval0.8833 nDCG@10
Community-submitted result
Retrieval relevance (0–1; higher is better)
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
Quick take
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
Cohere does not publish one simple hosted token price for Embed 4 on the reviewed pricing page. Ask for the exact SaaS or private-deployment rate before comparing total cost.
Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space.
The large free-token allowance is an account-level commercial detail, not a permanent zero-cost guarantee. Confirm eligibility, retention settings, and the rate that applies after the allowance.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Embeddings & vector search | Cohere Embed 4 | Voyage 4 Large |
|---|---|---|
| Embedding priceCurrent provider price per million input tokens or the closest published billing unit. | Hosted unit price not published | $0.12 / 1M tokens after 200M free |
| Input capacityMaximum content accepted in one embedding input, using the provider's documented token basis. | 128K tokens | 32K tokens |
| Vector dimensionsSupported output sizes; smaller vectors reduce storage while larger vectors may preserve more information. | 256, 512, 1,024, or 1,536 | 1,024 default; 256, 512, or 2,048 optional |
| Accepted inputsText, code, image, audio, video, PDF, or document-aware input supported by the endpoint. | Text, images, and mixed-content PDFs | Text and code |
| Retrieval controlsQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval. | Search query/document, classification, and clustering input types | Query/document input types, truncation, output dimension |
| Where it runsDirect API, cloud marketplace, private deployment, or self-hosted route documented by the provider. | Cohere API, Model Vault, Microsoft Foundry, SageMaker | Voyage API, MongoDB Atlas, and selected clouds |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Cohere enterprise customers can opt out of training; SaaS prompts and generations are generally deleted after 30 days. Approved zero-data-retention accounts and private deployments offer stronger controls.
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.
Provider and API links
Frequently asked questions
Cohere Embed 4: Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window. 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.
Consider Cohere Embed 4 when your priority is Enterprise search over visually rich documents. Consider Voyage 4 Large when your priority is Quality-sensitive text retrieval. Test both with your own data and provider route before committing.
No. This comparison aligns provider-published facts for the Embeddings & vector search category. It does not claim a universal winner or combine incompatible third-party benchmark scores.
