Screenshots 5
Cohere Embed v4
Summary
Multimodal embedding model supporting text and images with 128K token context for semantic search and retrieval systems.
Cohere Embed v4 transforms text, images, and mixed content into unified vector representations for semantic search, RAG, document clustering, and similarity matching. The model supports 1,536-dimensional embeddings with flexible compression via Matryoshka embeddings (256, 512, 1024, 1536 dimensions). Priced at $0.12/1M text tokens and $0.47/1M image tokens, it delivers multimodal capabilities competitive with text-only alternatives. The API supports batch processing up to 128,000 tokens per request with asymmetric search optimization. Limitation: incompatible with v3 embeddings; corpus re-embedding required for upgrades.
Bottom line: *Use for multimodal retrieval, document understanding, and vector search requiring unified text-image embeddings. Avoid for text-only applications where cheaper models suffice or when legacy v3 embeddings must be preserved.*
Pricing Plans
Per-token- Price
- $0.12 per 1M text tokens; $0.47 per 1M image tokens
- Cost per 1M Input
- $0.12
- Cost per 1M Output
- N/A (embedding model)
- Free Tier
- Trial API key available with rate limits; not for production or commercial use
Pay-As-You-Go (Text)
Text embedding pricing at $0.12 per 1 million input tokens with no monthly minimum
- Text to vector conversion
- Up to 128K token batch size
- 1,536-dim default output
- Matryoshka dimension flexibility
Pay-As-You-Go (Images)
Image embedding pricing at $0.47 per 1 million image tokens
- Image to vector conversion
- Supports single image per request
- Multimodal processing
- Up to 2.4M pixel resolution
Trial API Key
Rate-limited free tier for development and proof-of-concept; not permitted for production use
- All model capabilities
- Rate-limited calls
- Non-commercial only
- API key auto-generated on signup
Enterprise
Volume discounts and custom agreements for high-throughput workloads (billions of tokens monthly)
- Custom pricing negotiation
- Dedicated support
- SLAs available
- Private deployment options
View full pricing on cohere.com →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Unified multimodal model reduces infrastructure complexity
- Competitive pricing at $0.12/1M tokens for text embeddings
- Flexible output dimensions (256-1536) via Matryoshka embeddings reduce storage and latency
- Strong MTEB performance (65.2) with 35% cross-lingual retrieval improvement
- Supports asymmetric search for optimized query-document retrieval
Cons
Sign in to edit- Embed v4 vectors incompatible with v3; requires full corpus re-embedding for migrations
- Image pricing ($0.47/1M tokens) is higher than text and limits image-heavy workloads
- Trial keys rate-limited and unusable for production, requiring immediate production key conversion
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Cohere Platform, AWS Bedrock, Azure AI Foundry, Amazon SageMaker, GitHub Models
- Languages
- English and 100+ languages for text input; English for image input
- API Available
- Yes
- Self-Hosted
- No
- Last Updated
- 2026-04-13T13:01:28.770Z
Best For
Who it's for
- Production semantic search requiring multimodal support
- Large-scale document understanding and clustering
- Multilingual retrieval systems
- Cost-sensitive embedding operations at scale
- RAG systems with mixed text-image content
What it does well
- Semantic search and document retrieval
- Multimodal RAG (text and images from PDFs, slides)
- Document clustering and classification
- Visual and text similarity matching
- Cross-lingual retrieval systems
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Similar Tools
Compare Cohere Embed v4
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Cohere Embed v4 free?
- Cohere Embed v4 is a paid tool ($0.12 per 1M text tokens; $0.47 per 1M image tokens). A 0-day free trial is available.
- Is Cohere Embed v4 open source?
- No — Cohere Embed v4 is a closed-source tool. Source code is not publicly available.
- Does Cohere Embed v4 have an API?
- Yes. Cohere Embed v4 exposes a developer API. See the official documentation at https://cohere.com for details.
- When was Cohere Embed v4 released?
- Cohere Embed v4 was first released in 2025.
- What platforms does Cohere Embed v4 support?
- Cohere Embed v4 is available on: Cohere Platform, AWS Bedrock, Azure AI Foundry, Amazon SageMaker, GitHub Models.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Embed v4 is Cohere’s unified multimodal embedding model released in April 2025. It processes text, images, and interleaved multimodal content in a single model, outputting 1,536-dimensional vectors by default. The model supports multiple embedding formats (float, int8, uint8, binary, ubinary, base64) and configurable output dimensions (256, 512, 1024, 1536) via Matryoshka Representation Learning.
The model achieves 65.2 MTEB retrieval score and demonstrates 35% improvement in cross-lingual retrieval over prior versions. It supports up to 128,000 tokens per request for batch operations and handles images up to 2,458,624 pixels. Asymmetric search optimization differentiates document vs. query embeddings for improved retrieval accuracy in RAG systems.
Available via Cohere Platform, AWS Bedrock, Azure AI Foundry, and SageMaker. Pricing structure: text at $0.12 per million tokens, images at $0.47 per million tokens, with pay-as-you-go billing. Enterprise customers may negotiate volume discounts.
Key architectural difference: Embed v4 embeddings are not backward-compatible with v3; migrating requires re-embedding the entire corpus. The model supports 100+ languages for text input and English for image input.