Sold by: Multiverse Computing
Deployed on AWS
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI HyperNova 60B. In direct benchmarks against Mistral 3 Large, HyperNova 60B delivers outstanding gains:
Overview
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI HyperNova 60B. In direct benchmarks against Mistral 3 Large, HyperNova 60B delivers outstanding gains.
Highlights
- 12% higher intelligence index
- 92% lower memory usage
- 2.8x higher throughput, 65% faster latency
Details
Sold by
Categories
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
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.g5.48xlarge Inference (Batch) Recommended | Model inference on the ml.g5.48xlarge instance type, batch mode | $3.06 |
ml.g5.48xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.48xlarge instance type, real-time mode | $3.06 |
ml.g6.48xlarge Inference (Batch) | Model inference on the ml.g6.48xlarge instance type, batch mode | $2.73 |
ml.g6.48xlarge Inference (Real-Time) | Model inference on the ml.g6.48xlarge instance type, real-time mode | $2.73 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $8.21 |
ml.p5e.48xlarge Inference (Real-Time) | Model inference on the ml.p5e.48xlarge instance type, real-time mode | $14.78 |
Dimensions summary
You pay by the host hour based on the AWS instance type you run and your inference mode. Pricing has two modes: batch processing for grouped workloads and real-time for live responses. Batch mode runs on two instance types, each priced separately. Real-time mode runs on four instance types, each priced separately. Larger or more powerful instances carry higher hourly rates. You choose the instance that fits your performance needs and pay only for the hours you use, with no upfront commitment.
Top-of-mind questions for buyers
One host hour is one hour that a single inference instance runs the model. You are billed per running instance per hour. Charges accrue while the instance is active, whether in batch or real-time mode. The rate depends on which AWS instance type you select.
Batch mode processes grouped workloads and runs on two instance types. Real-time mode serves live responses and runs on four instance types. Both bill per host hour while the instance runs. Batch suits scheduled or bulk jobs. Real-time suits interactive, on-demand requests needing immediate output.
Software charges apply per host hour while the instance runs. A fully stopped instance stops accruing host hour charges. Underlying AWS infrastructure fees, such as storage, may still apply separately. The software meter counts running time only, in both batch and real-time modes.
multiversecomputing.com
Helpful?
Vendor refund policy
Placeholder
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
CompactifAI HyperNova 60B inference on a vLLM engine
Additional details
Inputs
- Summary
Our model accepts an input compatible with openAI's chat completions endpoint.
- Input MIME type
- application/json
{ "model": "cai-hypernova-60b", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Tell me about quantum computing."} ] }
{ "model": "cai-hypernova-60b", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Tell me about quantum computing."} ] }
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
Hypernova-60B v2602 is an enhanced version of the Hypernova-60B model, introducing improved tool-calling capabilities built on a compressed GPT-OSS-120B derived architecture. It maintains frontier-level reasoning performance while operating at roughly half the model size through targeted knowledge distillation. The update primarily focuses on stronger agentic workflows and reliable tool interaction.
HyperAccel delivers a fast and efficient LLM inference system on AWS F2 Instances. Our custom AI chip, the LLM Processing Unit (LPU), is the world's first hardware dedicated to end-to-end inference of large language models like Llama, HyperCLOVA X, and EXAONE.
HyperStart CLM is an AI-powered contract lifecycle management platform built for fast-moving, innovative teams. It cuts contracting time by up to 80% by enabling one-click import of legacy contracts from email, drives, or CRMs, and uses AI to extract metadata, automate renewals, and track obligations. HyperStart brings end-to-end visibility, structure, and efficiency to the entire contracting process.
HyperVerge offers seamless AI-based solutions for identity verification (KYC) and business verification (KYB) solutions that facilitate customer onboarding. We help build an ideal end-to-end solution that verifies identity, prevents fraud, and increases conversion rates for companies in Fintech, BFSI, Insurance, Lending, Gaming, Logistics, and EdTech across 195+ countries with over a billion identities verified across more than 450 companies. Prevent fraud and onboard users with secure and seamless ID verification!
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.