Sold by: Cohere
Deployed on AWS
Free Trial
Cohere provides a multilingual representative AI model, that translates texts and images into numerical vectors that models can understand.
Overview
Embed Light translates text and images into numerical vectors that models can understand. The most advanced generative AI apps rely on high-performing embedding models to understand the nuances of user inputs, search results, and documents. Embed Light is a smaller version of Embed with 384 dimensions. This version is also a multilingual model that supports 100+ languages and can be used to search within a language (e.g., search with a French query on French documents) and across languages (e.g., search with a Chinese query on Finnish documents). As of July 2025, the minimum requirement to deploy this model is CUDA version 12.2 and NVIDIA driver 535.
Highlights
- Embed is the market leading multimodal meaning text and images representation model used for semantic search, retrieval-augmented generation, classification, and clustering. As of Nov 2023 these models achieve state-of-the-art performance among 90+ models on the Massive Text Embedding Benchmark and SOTA for zero-shot dense retrieval on BEIR. As of September 2024 these models achieve state-of-the-art performance on a variety of text-to-image retrieval benchmarks.
- Our optimized containers enable low latency inference on a diverse set of hardware accelerators available on AWS providing different cost and performance points for SageMaker customers.
- Embeddings, Semantic Search, Retrieval-Augmented Generation (RAG), Text Classification, Clustering, Multilingual
Details
Sold by
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
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
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor.
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 | Description | Cost/host/hour |
|---|---|---|
ml.g4dn.12xlarge Inference (Batch) Recommended | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $19.80 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $5.71 |
ml.p3.2xlarge Inference (Real-Time) | Model inference on the ml.p3.2xlarge instance type, real-time mode | $15.49 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $6.16 |
ml.g4dn.xlarge Inference (Real-Time) | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $2.98 |
ml.g4dn.2xlarge Inference (Real-Time) | Model inference on the ml.g4dn.2xlarge instance type, real-time mode | $3.81 |
Vendor refund policy
No refunds. Please contact support+aws@cohere.com for further assistance.
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
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
🆕 Features
- Request Priority: Added priority field to chat, embed and rerank requests. High priority requests are handled first, and dropped last when the system is under load, ensuring lower latency and higher availability for high priority requests when there’s a mix of workloads with different latency requirements (e.g. realtime user requests and background batch jobs) 🐛 Bug Fixes Improved sparse embedding efficiency:
- Removed padded tokens from sparse embedding responses to reduce unnecessary computation and enhance accuracy for token-sparse inputs.
- Enhanced similarity calculation: Adopted cosine similarity (cosineSim) for more precise relevance scoring in embedding comparisons.
- Validated stability: Completed end-to-end testing in production and staging environments to ensure reliability. Temporary parameter limit: Restricted max_n to optimize performance during initial rollout (to be adjusted in a future update).
Additional details
Inputs
- Summary
The model accepts JSON requests that specifies the input text or a data url of a base64 encoded image to be embedded. The model does not accept both text and images in the same request. { "texts": [ "hello", "goodbye" ], "input_type": "search_query", "truncate": "END" } // OR for images { "images": [ "data:image/png;base64,/9j/4betRXhpZgA....."//Some image converted to base64 and formated as a data url ], "input_type": "search_query", "truncate": "END" }
- Input MIME type
- application/json
https://github.com/cohere-ai/cohere-aws/blob/main/examples/sample_embed_multilingual_light_v3_data.json
https://github.com/cohere-ai/cohere-aws/blob/main/examples/sample_embed_multilingual_light_v3_data.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
texts | An array of strings for the model to embed. Maximum number of texts per call is 1024. We recommend reducing the length of each text to be under 512 tokens for optimal quality. | Type: FreeText
| Yes |
images | An array of base 64 encoded data url as strings to embed. Maximum number of images per call is 1 | Default value: [] Type: FreeText | No |
input_type | A required field that will prepend special tokens to differentiate each type from one another. You should not mix different types together. The only exception for mixing types would be for search and retrieval, you should embed your corpus with the type search_document and then queries should be embedded with type search_query. | Type: Categorical Allowed values: search_document, search_query, classification, clustering | Yes |
truncate | One of NONE|LEFT|RIGHT to specify how the API will handle inputs longer than the maximum token length. Passing LEFT will discard the start of the input. RIGHT will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model. If NONE is selected, when the input exceeds the maximum input token length an error will be returned. | Default value: NONE Type: Categorical Allowed values: NONE, LEFT, RIGHT | No |
embeddings_type | Specifies the types of embeddings you want to get back. Not required. If unspecified, returns the float response type. Can be one or more of the types specified in Allowed Values. | Default value: NONE Type: Categorical Allowed values: float, int8, uint8, binary, ubinary | No |
Resources
Vendor resources
Support
Vendor support
Contact us at support+aws@cohere.com or join our Discord community at https://discord.com/invite/co-mmunity
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
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents in over 100 languages.
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents.
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents.
Rerank improves search systems by sorting documents based on their semantic similarity to a query.
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents in over 100 languages.
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.