Sold by: Cohere
AWS Free Tier
Embed 4 transforms multiple modalities, such as texts and images, into numerical vectors.
Overview
Embed 4 is a multilingual multimodal embedding model. It is capable of transforming different modalities such as images, texts, and interleaved images and texts into a single vector representation. Embed 4 offers state-of-the-art performance across all modalities (texts, images, interleaved texts and image) and in both English and multilingual settings.
Embed 4 offers a variety of ways for compression both on the number of dimensions and the number-format precision. The model offers byte and binary quantization and matryoshka embeddings for further compression.
Highlights
- Embed 4 offers State-of-the-art performance in Text-to-Text, Text-to-Image, and Text-to-Mixed Modality domains across 100+ languages.
- Embed 4 is capable of vectorizing interleaved texts and images and capturing key visual features from screenshots of PDFs, slides, tables, figures, and more, thereby eliminating the need for complex document parsing.
- Embed 4 supports a 128k context length and an images can have a maximum of 2MM pixels.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/unit |
|---|---|
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Price per 1 million input tokens | $0.12 |
Dimensions summary
You pay for Cohere Embed 4 based on usage, measured per 1 million input tokens. A token is a chunk of text the model processes; simple text runs near one token per word. There are no upfront commitments or instance fees here. Two pricing categories exist: a standard per-1-million-input-tokens rate and a Global per-1-million-input-tokens rate. Each category repeats across multiple entries, reflecting different AWS Regions or deployment options that carry their own rate. You are charged only for the input tokens you send, so cost scales directly with how much text you embed.
Top-of-mind questions for buyers
A token is a chunk of text the model reads, not a whole word or character. Simple text runs near one token per word. Complex text with uncommon words may use three to four tokens per word. You are billed by input token volume, so denser text raises your token count.
Both charge per 1 million input tokens on a usage basis. The standard entries apply to specific AWS Regions, while the Global entries apply to a cross-region deployment option. Your rate depends on which deployment path you select. Charges apply only to input tokens you send in either case.
No. Billing is usage-based and tied only to input tokens processed. There are no upfront commitments or per-instance fees in this listing. When you send no text, no software charges accrue. Cost scales directly with the volume of text you embed.
cohere.com
Helpful?
Vendor refund policy
Cohere does not provide any refunds.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Connect your OpenAI, Anthropic, and Cohere applications to Amazon Bedrock by changing one base URL. 100+ models, plus images, audio, files and embeddings. Runs in your own AWS account.
CloudZone’s GenAI Innovation Workshop is a hands-on, results-driven engagement designed to empower organizations with the knowledge, tools, and best practices to harness Generative AI (GenAI) using Retrieval-Augmented Generation (RAG) frameworks on AWS.
Led by CloudZone architects and AI experts, this workshop walks your team through the end-to-end process of building GenAI capabilities with your own data — securely, efficiently, and aligned with your business use cases. The workshop includes curated demos, live exercises, and an actionable roadmap tailored to your technical maturity.
This solution is ideal for organizations looking to unlock the value of unstructured content (emails, documents, chats, PDFs, etc.) by combining it with powerful Foundation Models (FMs) — without the need to train models from scratch.
Seamlessly migrate your GenAI workloads from OpenAI APIs to Amazon Bedrock with a secure, scalable, and cost-optimized approach.
Gencore AI enables businesses to build safe, enterprise-grade AI systems, copilots, and agents within minutes by leveraging proprietary data across various systems and applications while utilizing any AI model from Amazon Bedrock and Amazon SageMaker.
ECV Shopping Assistance AI is an enterprise generative AI commerce assistant that provides personalized product discovery, contextual recommendations, and conversational customer support for e-commerce and retail businesses. Delivered as an embeddable web widget and a LINE messaging integration, the solution helps online shoppers find what they are looking for, ask questions about products, and complete purchases without having to manually search or navigate the catalog.
Built on top of the AI Enterprise Assistant (ECVBot) platform and powered by Amazon Bedrock with Anthropic Claude foundation models, the solution combines retrieval-augmented generation (RAG) over the merchant's product catalog and content with conversational AI tuned for retail commerce interactions.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.