Sold by: JetBrains Americas
Deployed on AWS
Mellum All is JetBrains' large language model (LLM) optimized for code completion in all languages.
Overview
Mellum All is JetBrains' large language model (LLM) optimized for code completion in all languages.
Highlights
- LLaMA-like architecture with ~4B parameters.
- Context-aware code completion with fill-in-the-middle.
- Top quality-to-size ratio.
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
This product is available free of charge. Free 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.
Dimensions summary
This listing is free to use, so you pay only for the AWS compute you run. Pricing is organized by the instance type you pick and how you run inference. You can choose batch mode or real-time mode on the ml.g5.2xlarge instance. The other instances — ml.g6.2xlarge, ml.g6e.xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p5.48xlarge, and ml.p5e.48xlarge — run in real-time mode only. Each option bills per host hour (HostHrs). More capable instance types generally carry higher hourly compute costs. You match the instance to your latency and throughput needs.
Top-of-mind questions for buyers
Billing accrues per host hour (HostHrs) while an instance runs. The software itself is free, so you pay only for active AWS compute time. Fully stopped instances do not accrue host-hour charges. Any underlying AWS storage attached to a stopped instance may still incur separate AWS fees.
One host hour covers a single running instance of the chosen type for one hour. It reflects the full compute node, including its GPUs, not per-user or per-request usage. The model runs efficiently on GPU hardware, letting one instance serve many concurrent requests within that hour.
Both bill per host hour on the same instance type. Real-time mode serves live, low-latency requests as they arrive. Batch mode processes grouped inputs together, which suits large jobs without immediate response needs. You pick the mode based on whether responses must return in milliseconds.
www.jetbrains.com
Helpful?
Vendor refund policy
This product is free.
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 version available to enterprise customers.
Additional details
Inputs
- Summary
Model input should be application/json. See the input parameters and sample input data for more information.
- Input MIME type
- application/json
{"prefix": "import js", "suffix": "\n", "filepath": "main.py", "context": [], "max_length": 32, "stop_token": "\n\n", "use_control": "off"}
{"prefix": "import js", "suffix": "\n", "filepath": "main.py", "context": [], "max_length": 32, "stop_token": "\n\n", "use_control": "off"}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
prefix | Code that appears before the cursor. | string | Yes |
suffix | Code that appears after the cursor. | string | Yes |
filepath | Relative path of the file being edited, including file name and extension (e.g. 'src/utils/helpers.ts'). | string | Yes |
context | Additional context items (such as neighbouring files, docs, etc.) | list | No |
max_length | Maximum number of BPE tokens that may be generated for the completion snippet. | integer | Yes |
stop_token | String at which generation should stop (exclusive). | string | No |
use_control | Selects the Cloud-Control mode. Use 'off' if unsure. | "on","off","silent" | Yes |
generate_indents | Whether the model should emit indentation characters. | boolean | No |
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
Mellum All is JetBrains' large language model (LLM) optimized for code completion in all languages.
JetBrains IDE Services is a developer experience suite that accelerates software development while making developer tools easy to manage at scale.
Mellum Python is JetBrains' large language model (LLM) optimized for code completion in python.
Mellum Kotlin is JetBrains' large language model (LLM) optimized for code completion in Kotlin and Java languages.
The ultimate CI/CD solution built to scale with your DevOps needs.
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.