All models
Cohere
Cohere Embed 4
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
Plain-English overview
What Cohere Embed 4 actually is
Cohere Embed 4 is designed for search over normal prose and documents whose meaning depends on layout or visuals. It can embed text, images, and mixed-content PDFs, which is useful for slide decks, reports, diagrams, and scanned business material.
The endpoint supports several vector sizes and compact numerical formats. Query, document, classification, and clustering input types let the same model shape representations around the task rather than treating every input identically.
Good fit for
- Enterprise search over visually rich documents
- Multilingual RAG and semantic search
- Organizations that need private deployment choices
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
- Hosted unit price not publishedCurrent provider price per million input tokens or the closest published billing unit.
- Input capacity
- 128K tokensMaximum content accepted in one embedding input, using the provider's documented token basis.
- Vector dimensions
- 256, 512, 1,024, or 1,536Supported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
- Accepted inputs
- Text, images, and mixed-content PDFsText, code, image, audio, video, PDF, or document-aware input supported by the endpoint.
- Retrieval controls
- Search query/document, classification, and clustering input typesQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval.
- Where it runs
- Cohere API, Model Vault, Microsoft Foundry, SageMakerDirect 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.
Cohere Embed 4 · FinanceBenchRetrieval
Community-submitted result
Retrieval relevance (0–1; higher is better)
Test configuration
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
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.
Cohere Embed 4
Cohere
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
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 Cohere Embed 4
Availability
Regions and access stage
Available through Cohere's Embed API, with private deployment and selected cloud-platform routes for enterprise customers.
Processing location and residency depend on the Cohere platform, private environment, or chosen cloud marketplace agreement.
Check live availabilityData and training
The route matters.
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.
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
Cohere Embed 4 FAQ
What is Cohere Embed 4?
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window. Cohere Embed 4 is designed for search over normal prose and documents whose meaning depends on layout or visuals. It can embed text, images, and mixed-content PDFs, which is useful for slide decks, reports, diagrams, and scanned business material.
When was Cohere Embed 4 released?
Cohere Embed 4 was released on April 15, 2025 according to the cited provider materials.
Where can I access Cohere Embed 4?
Available through Cohere's Embed API, with private deployment and selected cloud-platform routes for enterprise customers. The access routes listed in this guide are Cohere, Microsoft Foundry, and AWS SageMaker.
How much does Cohere Embed 4 cost?
Hosted unit price not published. Cohere's reviewed public pricing page does not state one comparable hosted Embed 4 token rate. Model Vault and private deployments use capacity or contract pricing.
Where is Cohere Embed 4 available?
Available through Cohere's Embed API, with private deployment and selected cloud-platform routes for enterprise customers. Processing location and residency depend on the Cohere platform, private environment, or chosen cloud marketplace agreement.
Is my Cohere Embed 4 API data used for training?
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. 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
- 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
Cohere Embed 4 vs Gemini Embedding 2
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.
Open full comparisonCohere Embed 4 vs text-embedding-3-large
OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.
Open full comparisonCohere Embed 4 vs 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.
Open full comparisonCohere Embed 4 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 comparisonCohere Embed 4 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 comparisonCohere Embed 4 vs Mistral Embed
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.
Open full comparison