Sold by: Takara
Deployed on AWS
Free Trial
Takara's DS1 Embedding Model is a high-speed, low-computing text embedding solution, leveraging static embeddings for superior performance. Offering exceptional speed and near-OpenAI accuracy, it's ideal for applications demanding swift semantic responses, such as speech-to-speech, betting, and gaming. With an API compatible with OpenAI, DS1 ensures a seamless upgrade experience.
Overview
Takara's DS1 Embedding Model is a high-speed text embedding model that employs static embeddings, eliminating the need for a GPU model for embeddings. This innovative feature significantly reduces computing requirements, while still maintaining an impressive performance. Although DS1 is much faster than standard embeddings like OpenAI, it does not compromise on accuracy, delivering results that are nearly as precise. The DS1 API is fully compatible with OpenAI's API, facilitating a smooth drop-in replacement strategy for application upgrades. DS1 is particularly effective in scenarios where speed is paramount, such as in speech-to-speech applications where latency is critical, or in near-real-time applications like betting and gaming that demand a rapid semantic approach.
Highlights
- Exceptional Speed: Optimized for CPUs, DS1 delivers the same performance as GPU-based models, maintaining quality on par with GPU-based embeddings. With a lLatency of 0.97 ms for a single query with at most 512 tokens. 1,640M tokens per hour at $0.01 per 1M tokens on an ml.c5.2xlarge instance.
- Reduced Dimension & Cost: With an embedding dimension of 512, DS1 is 6-8x smaller compared to OpenAI (3072) and E5 Mistral (4096), resulting in a significant reduction in vectorDB costs.
- Seamless Integration: DS1 serves as a drop-in replacement for OpenAI embeddings, ensuring a smooth transition and upgrade process.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
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
Free trial
Try this product free for 21 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.c5.2xlarge Inference (Batch) Recommended | Model inference on the ml.c5.2xlarge instance type, batch mode | $2.46 |
ml.c5.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.c5.2xlarge instance type, real-time mode | $2.46 |
ml.c5.xlarge Inference (Batch) | Model inference on the ml.c5.xlarge instance type, batch mode | $1.20 |
ml.c5.4xlarge Inference (Batch) | Model inference on the ml.c5.4xlarge instance type, batch mode | $4.92 |
ml.c5.9xlarge Inference (Batch) | Model inference on the ml.c5.9xlarge instance type, batch mode | $11.04 |
ml.c5.18xlarge Inference (Batch) | Model inference on the ml.c5.18xlarge instance type, batch mode | $22.02 |
ml.c5.xlarge Inference (Real-Time) | Model inference on the ml.c5.xlarge instance type, real-time mode | $1.20 |
ml.c5.4xlarge Inference (Real-Time) | Model inference on the ml.c5.4xlarge instance type, real-time mode | $4.92 |
ml.c5.9xlarge Inference (Real-Time) | Model inference on the ml.c5.9xlarge instance type, real-time mode | $11.04 |
ml.c5.18xlarge Inference (Real-Time) | Model inference on the ml.c5.18xlarge instance type, real-time mode | $22.02 |
Dimensions summary
You pay by the host hour for running this embedding model, with no upfront commitment. Pricing splits into two inference modes. Batch mode processes data in bulk and runs on five compute instance sizes, from ml.c5.xlarge up to ml.c5.18xlarge. Real-time mode serves live requests and runs on those same five sizes plus two smaller ml.t2.medium and ml.t2.large options. Within each mode, larger instances carry more compute capacity. You select the mode and instance size that fit your workload, and your cost scales with the hours each instance runs.
Top-of-mind questions for buyers
One host hour covers a single instance running the model for one hour. Billing meters the running time of the instance you deploy. Each instance size you launch accrues its own host hours. Your total reflects the number of instances and how long each one runs.
Batch mode processes data in bulk, suited to jobs run periodically on large datasets. Real-time mode serves live requests as they arrive, suited to low-latency applications. You pick the mode per workload. Each mode bills separately by host hour on its own instance types.
Software charges accrue only while an instance runs and meters host hours. Stopped instances stop accruing software charges. Underlying AWS infrastructure fees, such as storage, may still apply separately depending on your setup. To stop all software charges, shut down the instance.
takara.ai
Helpful?
Vendor refund policy
Refunds are furnished in line with the EULA only. Please contact support@takara.ai for 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
Updated documentation.
Additional details
Inputs
- Summary
The model accepts JSON requests that specifies the input text as s single string or an array to be embedded.
inputs: str or List[str] - Single text or list of texts. truncate: bool, optional (default=False) - True: Truncates. False: raises error if any given text exceeds the context length. truncation_direction: str, optional (default="right") - "right": truncates the right of the string; "left": truncates the left part of input string.
- Limitations for input type
- The maximum tokens for each text is 512, the maximum length of the list is 32.
{ "inputs": "Hello world" }
{ "inputs": ["Hello world", "we have arrived!"] }
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | A string or array of strings for DS1 to embed. The maximum size a string to be embedded is 512. and the maximum number of strings per call is 32. | 512 tokens maximum. | Yes |
truncate | One of True | False to specify how the API will truncate inputs longer than the maximum token length. | Defaults to False | No |
truncation_direction | Determines how truncation of the string happens when truncate is set to True. 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 DS1. | - | No |
Support
Vendor support
Please email support@takara.ai for customer support for next day response.
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
Takara's DS1 Embedding Model is a high-speed, low-computing text embedding solution that now supports multiple languages, leveraging static embeddings for superior performance. Offering exceptional speed and near-OpenAI accuracy across global markets, it's ideal for applications demanding swift semantic responses, such as speech-to-speech, betting, and gaming. With an API compatible with OpenAI, DS1 ensures a seamless upgrade experience without language barriers.
Takara's ds1-code, powering Miru, is a CPU-based code embedding and retrieval model that gives AI coding agents precise, semantic access to a codebase without burning tokens on wasteful search. Delivering over 50% token reduction, 40%+ lower token costs, and up to 60% faster retrieval, Miru works underneath Claude Code, Cursor, Codex, GitHub Copilot, and other coding agents to cut inference spend while preserving generated code quality.
A cloud native EMV 3D Secure 3DS Authentication Platform designed for secure, frictionless, and compliant cardholder verification. Built on AWS for high availability and scalability, it enables issuers, payment gateways, and financial institutions to reduce fraud, improve approval rates, and deliver seamless Strong Customer Authentication SCA. Supports EMV 3DS 2.x, risk based authentication, advanced security controls, and real time monitoring for superior performance and regulatory compliance.
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.