Sold by: Inception
Deployed on AWS
Free Trial
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions.
Overview
Diffusion-based approach to language generation is pioneered and inspired by advanced AI systems for images and video like Midjourney and Sora and provides unprecedented speed, quality, and generative control. Our diffusion large language models (dLLMs) provide: 1. Unparalleled speed 2. Improved efficiency 3. Enhanced quality.
Highlights
- Unparalleled speed - 5-10X faster than traditional LLMs.
- Improved efficiency - 5-10X cheaper than traditional LLMs.
- Enhanced quality - 2X model size with the same latency and cost.
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
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.g5.12xlarge Inference (Batch) Recommended | Model inference on the ml.g5.12xlarge instance type, batch mode | $5.00 |
ml.p5.48xlarge Inference (Real-Time) Recommended | Model inference on the ml.p5.48xlarge instance type, real-time mode | $6.25 |
ml.g5.24xlarge Inference (Batch) | Model inference on the ml.g5.24xlarge instance type, batch mode | $5.00 |
ml.g5.48xlarge Inference (Batch) | Model inference on the ml.g5.48xlarge instance type, batch mode | $5.00 |
Dimensions summary
You pay by the host-hour, based on the compute instance you run and the inference mode. Three batch-mode dimensions run on progressively larger GPU instance types: ml.g5.12xlarge, ml.g5.24xlarge, and ml.g5.48xlarge. Batch mode processes grouped requests. A fourth dimension covers real-time inference on the ml.p5.48xlarge instance, which returns responses immediately. Your cost scales with the instance size you select and how many hours you run it. Choose a batch dimension for scheduled workloads or the real-time dimension for interactive use. Each dimension bills independently by usage.
Top-of-mind questions for buyers
A host-hour meters one running compute instance for one hour of model inference. You pay for each hour the instance stays active, regardless of how many requests it handles. The instance type you pick sets the GPU capacity behind the model. Stopping the instance ends the host-hour charges.
Both meter running instance-hours, but they serve different workloads. Batch mode groups queued requests and processes them together, suiting scheduled or high-volume jobs. Real-time mode returns responses immediately for interactive use like chat or voice agents. You are billed per host-hour in either case, based on the instance you run.
Host-hour charges accrue while the instance is running, whether or not it processes requests. An idle but active instance still bills per hour. Stopping the instance ends software host-hour charges. Underlying AWS storage or other resource fees may continue separately depending on your setup.
www.inceptionlabs.ai
Helpful?
Vendor refund policy
Please contact support@inceptionlabs.ai if you require a refund for any reason.
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
- First release
Additional details
Inputs
- Summary
Our model takes inputs in OpenAI-compatible chat completions format:
{ "messages": [ { "role": "user", "content": "Hello! How are you?" } ], "stream": false, "max_tokens": 1024 }
{
"messages": [
{
"role": "user",
"content": "Hello! How are you?"
}
],
"stream": false,
"max_tokens": 1024
}
{
"messages": [
{
"role": "user",
"content": "Hello! How are you?"
}
],
"stream": false,
"max_tokens": 1024
}
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
Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Coder Small's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the blog https://www.inceptionlabs.ai/introducing-mercury.
MySQL server comes pre-installed on Windows Server 2019 running MySQL Community Edition, PHP, Apache, PhpMyadmin & MySQL Workbench using XAMPP.
This daily dataset is best for analyzing the pricing and trading patterns of Mercury classic cars in the secondary markets via auctions and online sales. It contains 20+ years of sales records across vendors in North America, Europe and Asia.
The product has charges associated with it for support, maintenance, and pre-configuration to be instantaneously deployed on AWS Marketplace with all security and enterprise standards. Trac Auth on Ubuntu server 24.04 Image is packaged to leverage cost-effectiveness, scalability, and flexibility.
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.