Skip to main content
Cohere ↗Released March 1, 2025

Cohere Embed v4

Undisclosed parameters

Cohere Embed v4 is Cohere's entry in a crowded field. Context window: 0.128K tokens.

Context

128K

Input

$0.12

Key Specifications

🏆

Arena Rank

Not disclosed

📐

Context Window

128K

📥

Input Price

per 1M tokens

$0.12

📤

Output Price

per 1M tokens

$0.12

🧠

Parameters

Undisclosed

🔒

Open Source

No

Best For

Semantic searchRAG embeddingsdocument retrieval

About Cohere Embed v4

Cohere Embed v4, developed by Cohere, is the first multimodal embedding model in Cohere's lineup, processing both text and images into unified 128K-context vector representations. The model generates embeddings for semantic search, RAG pipelines, document retrieval, and visual search applications. Supporting 100+ languages, Embed v4 produces compact, efficient vectors optimized for modern vector databases. Its multimodal capability enables searching across mixed document types containing both text and visual elements. Priced at $0.12 per million tokens, it offers affordable embedding generation for production applications. The model represents a significant upgrade over text-only Embed v3, enabling unified search across document types. It is particularly valuable for enterprises with heterogeneous content including PDFs, presentations, and image-heavy documents that require combined text and visual understanding.

Built byCohere↗

Pricing per 1M tokens

Input Tokens

$0.12

Output Tokens

$0.12

Compare Cohere Embed v4

See how Cohere Embed v4 stacks up against other leading AI models

Cohere Embed v4 vs Command R+Compare →Cohere Embed v4 vs Command RCompare →Cohere Embed v4 vs Aya 23 35BCompare →Cohere Embed v4 vs Aya ExpanseCompare →Cohere Embed v4 vs Cohere Embed v3Compare →

Other Cohere Models

Command R+
128K#17
Command R
128K#23
Aya 23 35B
8K
Aya Expanse
128K
Cohere Embed v3
512 tokens

Other Top Models

Claude Opus 4Anthropic
#1
GPT-o3OpenAI
#2
GPT-4oOpenAI
#2
GPT-o1OpenAI
#3
DeepSeek R1DeepSeek
#3
Claude Sonnet 4Anthropic
#3

Explore More

Model Benchmarks →All Models →Cohere Company Profile →

Frequently Asked Questions

What is Cohere Embed v4?▾
Cohere Embed v4, developed by Cohere, is the first multimodal embedding model in Cohere's lineup, processing both text and images into unified 128K-context vector representations. The model generates embeddings for semantic search, RAG pipelines, document retrieval, and visual search applications. Supporting 100+ languages, Embed v4 produces compact, efficient vectors optimized for modern vector databases. Its multimodal capability enables searching across mixed document types containing both text and visual elements. Priced at $0.12 per million tokens, it offers affordable embedding generation for production applications. The model represents a significant upgrade over text-only Embed v3, enabling unified search across document types. It is particularly valuable for enterprises with heterogeneous content including PDFs, presentations, and image-heavy documents that require combined text and visual understanding.
How much does Cohere Embed v4 cost?▾
Cohere Embed v4 costs $0.12 per 1M input tokens and $0.12 per 1M output tokens. You pay only for what you use, which keeps costs predictable.
What is Cohere Embed v4's context window?▾
Cohere Embed v4 has a context window of 128K tokens. This determines how much text the model can process in a single request — bigger windows mean longer documents and richer conversation history.
Is Cohere Embed v4 open source?▾
No, Cohere Embed v4 is a proprietary model available through Cohere's API. You get managed infrastructure, regular updates, and support as part of the package.
What is Cohere Embed v4 best for?▾
Cohere Embed v4 is best suited for: Semantic search, RAG embeddings, document retrieval. These use cases play to the model's strengths in capability, speed, and cost within Cohere's lineup.