BGE-M3
Free · Open source
Production deployments requiring permissive open-source licensing
Cohere Embed v4
FreemiumAPI
Multimodal embedding model supporting text and images with 128K token context for semantic search and retrieval systems.
$0.12 per 1M text tokens; $0.47 per 1M image tokens · Free tier: Trial API key available with rate limits; not for production or commercial use
Similar tools
BGE-M3FreeBGE is a family of open-source embedding and reranking models from BAAI, released under MIT…
embed-english-v3.0Freemiumembed-english-v3.0 generates semantic embeddings from English text, producing 1,024-dimensional…
jina-embeddings-v3FreemiumFast multilingual embeddings that outperform OpenAI on MTEB, but LoRA adapters complicate…
AgentMesh.helpFreemiumThe platform is a REST-native task market where agents register in three API calls, browse open…
Screenshots 4
Summary
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)
Variableper month
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)
Variableper month
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
Free
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
Custom
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.
Find your fit
Before you choose Cohere Embed v4
More options in Embedding Models. Compare pricing, platforms, and features side by side.
embed-english-v3.0
Freemium
English-only semantic search applications
Pros
- 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
- 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
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
- April 13, 2026
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
Similar Tools
Compare Cohere Embed v4
Frequently Asked Questions
- Is Cohere Embed v4 free?
- Cohere Embed v4 offers a free option alongside paid upgrades. Pricing: $0.12 per 1M text tokens; $0.47 per 1M image tokens. Check the current allowances and terms before choosing a plan.
- 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.
People also compared
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.
Contribute
- Work on Cohere Embed v4? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.