Sold by: Multiverse Computing
Deployed on AWS
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI Mistral Small 3.1 Slim. A 50% compression of the widely known Mistral Small 3.1 model.
Overview
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI Mistral Small 3.1 Slim. A 50% compression of the widely known Mistral Small 3.1 model.
Highlights
- 70% Infrastructure OpEx Reduction
- 2x Faster Inference Throughput
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.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $0.98 |
ml.g5.12xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.12xlarge instance type, real-time mode | $0.98 |
ml.g5.16xlarge Inference (Batch) | Model inference on the ml.g5.16xlarge instance type, batch mode | $0.74 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $1.35 |
ml.g5.48xlarge Inference (Batch) | Model inference on the ml.g5.48xlarge instance type, batch mode | $2.57 |
ml.g5.16xlarge Inference (Real-Time) | Model inference on the ml.g5.16xlarge instance type, real-time mode | $0.74 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $1.35 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $2.57 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $3.15 |
ml.p5.48xlarge Inference (Real-Time) | Model inference on the ml.p5.48xlarge instance type, real-time mode | $7.72 |
Dimensions summary
You pay by the host hour for running inference on this compressed language model. Pricing depends on two choices. First, you pick an instance type, which sets the compute hardware. Options range across several g5 sizes plus p4d and p5 GPU instances. Larger instances carry higher hourly rates. Second, you pick an inference mode. Batch mode processes grouped requests, while real-time mode serves live responses. The g5 sizes offer both modes; the p4d and p5 instances offer real-time only. You are billed per hour of use, with no upfront commitment.
Top-of-mind questions for buyers
One host hour covers one hour of a running instance serving this compressed model. The instance type sets the GPU hardware and memory. You are charged per hour the instance runs, regardless of how many requests it processes. Fully stopped instances stop accruing software charges.
Both modes bill per host hour on the same instance. Batch mode processes grouped requests together, so an instance runs only while a job runs. Real-time mode keeps an instance active to serve live responses, accruing charges the whole time it stays up. Batch suits scheduled jobs; real-time suits continuous serving.
The p4d and p5 GPU instances are offered for real-time inference only, while the g5 sizes support both batch and real-time. If you need batch processing, choose a g5 instance. For higher-powered real-time serving, the p4d and p5 options are available.
multiversecomputing.com
Helpful?
Vendor refund policy
Placeholder Refund Policy
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 Mistral Small 3.1 Slim inference on a vLLM engine with text-only support
Additional details
Inputs
- Summary
Our model accepts an input compatible with openAI's chat completions endpoint.
- Input MIME type
- application/json
{
"model": "cai-mistral-3-1-small-slim",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Tell me about quantum computing."}
]
}
{
"model": "cai-mistral-3-1-small-slim",
"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
CompactifAI API empowers organizations with ultra-efficient and scalable AI models that slash compute and energy costs, accelerate deployment, and fuel innovation, all without compromising performance or reliability!
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI Llama 3.1 Slim. A 80% compression of the widely known Meta Llama 3.1 8B model.
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:
Reduce inference costs and increase inference speed by using Multiverse Computing's CompactifAI Llama 4 Scout Slim. A 50% compression of the widely known Meta Llama 4 Scout model.
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.