Sold by: Arcee AIÂ
Deployed on AWS
Enterprise-grade LLM offering deep customization, seamless integration, and top-tier security & compliance for businesses.
Overview
Arcee-SuperNova is an advanced general language model developed by Arcee AI, offering superior performance, customization, and security compared to traditional closed-source models. It excels in instruction following and human preference scores, outperforming Llama 70B-Instruct, as well Llama 405B, Claude Sonnet 3.5 and GPT-4o in many general benchmarks. SuperNova also provides businesses with the option for deep customization on their data and use cases, seamless integration into existing systems, and top-tier security & compliance. It's ideal for industries with stringent security requirements, data-driven companies, and businesses seeking cost efficiency, offering up to 95% cost reduction compared to closed-source models.
IMPORTANT INFORMATION: The model is available in two package versions. Please make sure to select the appropriate one. Once you have subscribed, we strongly recommend that you deploy it with our sample notebooks at https://github.com/arcee-ai/aws-samples .
Highlights
- ***Unmatched Performance & Customization*** * 60% better benchmarks with fewer hallucinations and faster responses * State-of-the-art instruction following ability * Deep customization on proprietary data and use cases * Seamless scalability within the AWS ecosystem * Regular updates with latest open-source tech, avoiding vendor lock-in
- ***Cost-Effective & Compliant Solution*** * Up to 96% cost reduction compared to closed-source models * Rapid ROI with quick and easy implementation * Eco-friendly GenAI with reduced operational costs * Future-proof compliance within EU AI Act's safe thresholds * Full data ownership and transparency
- ***Versatile Enterprise Applications*** * Ideal for industries with stringent security requirements (finance, healthcare, government) * Perfect for data-driven companies requiring tailored AI models * Suitable for businesses seeking cost efficiency without compromising performance * Use cases include customer service, content creation, data analysis, R&D, legal & compliance, and education & training
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
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.p3.8xlarge Inference (Batch) Recommended | Model inference on the ml.p3.8xlarge instance type, batch mode | $0.00 |
ml.p4d.24xlarge Inference (Real-Time) Recommended | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $3.77 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $0.00 |
ml.p4de.24xlarge Inference (Real-Time) | Model inference on the ml.p4de.24xlarge instance type, real-time mode | $4.71 |
ml.g6.12xlarge Inference (Real-Time) | Model inference on the ml.g6.12xlarge instance type, real-time mode | $1.15 |
ml.g6.24xlarge Inference (Real-Time) | Model inference on the ml.g6.24xlarge instance type, real-time mode | $1.76 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $1.42 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $11.31 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $2.04 |
Vendor refund policy
Given the nature of the service, we're unable to offer 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)Â .
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
This model package is configured for p4 and p5 8-GPU instances. Context size is 32 KB and the OpenAI Messages API is enabled.
Additional details
Inputs
- Summary
You can invoke the model using the OpenAI Messages AI. Please see the sample notebook for details.
- Input MIME type
- application/json, application/jsonlines
{
"messages": [
{
"role": "system",
"content": "As a friendly technical assistant engineer, answer the question in detail.",
},
{"role": "user", "content": "Why are transformers better models than LSTM?"},
],
"max_tokens": 256
}
https://github.com/arcee-ai/aws-samples/blob/main/model_package_notebooks/sample-notebook-arcee-supernova-on-sagemaker.ipynb
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
OpenAI Messages API | Please see sample notebook. | Type: FreeText | Yes |
Resources
Support
Vendor support
IMPORTANT INFORMATION: Once you have subscribed to the model, we strongly recommend that you deploy it with our sample notebook at https://github.com/arcee-ai/aws-samples . This is the only way to guarantee proper configuration and optimization. Due to the size of the model, deploying through the marketplace (e.g., with CloudFormation) may not work correctly and face download timeouts.
Bugs, questions, feature requests: please create an issue in the aws-samples repository on Github.
Contact: support@arcee.aiÂ
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
Arcee-SuperNova-Medius is a 14B parameter language model developed by Arcee.ai, built on the Qwen2.5-14B-Instruct architecture.
Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai.
Arcee Nova is a state-of-the-art 72-billion parameter language model developed by Arcee.ai.
Arcee-Lite is a compact yet powerful 1.5B parameter language model developed by Arcee.ai.
Arcee-Spark is a powerful 7B language model developed by Arcee.ai.
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.