Sold by: Cohere
Deployed on AWS
Free Trial
Command R 08-2024 is a generative language model optimized for large scale production workloads.
Overview
Command R 08-2024 is an updated highly performant generative large language model. It is designed to excel across a variety of use cases including reasoning, summarization, and question answering, with increased performance on coding, math, and reasoning. The model has the capability for multilingual generation evaluated in 10 key business languages, alongside pre-training for an additional 13 languages. With highly performant RAG capabilities, it is built for enterprises that plan to leverage their internal data and documents for a tailored and accurate language model. Batch transform is not supported with this model.
Highlights
- Command R 08-2024 utilizes retrieval-augmented generation (RAG) to deliver accurate and verified responses. This approach ensures credible and trustworthy interactions by providing clear and in-line citations for users to verify. With RAG, Command R 08-2024 can be grounded in internal documents and data, providing accurate and actional model outputs.
- Command R 08-2024 has a 128k token context window. This updated model excels at tool use, which can be implemented to build user-defined tools. These tools enable the model to automate highly sophisticated tasks using internal infrastructure as well as external tools.
- Command R 08-2024 is proficient in the 10 most commonly used business languages (Arabic, Mandarin, English, French, German, Italian, Spanish, Japanese, Korean, and Portuguese) and pre-trained on 13 additional languages, ensuring seamless understanding and response in various tongues. The model excels at long-context tasks such as: document summarization, content Q&A, long-form generation, and content generation amongst others. It can power knowledge assistants, chatbots, customer support agents and more.
Details
Sold by
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.g4dn.12xlarge Inference (Batch) Recommended | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $16.93 |
ml.p5.48xlarge Inference (Real-Time) Recommended | Model inference on the ml.p5.48xlarge instance type, real-time mode | $16.93 |
Dimensions summary
You pay by the hour for the compute instance that runs the model, not by token. Two options let you match the instance to your inference need. The ml.g4dn.12xlarge instance runs in batch mode, which processes grouped requests together. The ml.p5.48xlarge instance runs in real-time mode, which handles requests as they arrive. Each option is billed per host hour, so your cost scales with how long the instance runs. Choose the instance and mode that fit your workload's throughput and latency requirements.
Top-of-mind questions for buyers
The ml.g4dn.12xlarge instance uses GPU compute suited to batch inference, processing grouped requests together. The ml.p5.48xlarge instance is a higher-capacity GPU instance for real-time inference, handling requests as they arrive. Each bills separately per host hour. Your choice depends on whether you prioritize throughput or low latency.
Billing accrues per host hour while an instance runs. You pay for the time the instance is active, not for tokens processed. Stopping or terminating the instance ends software host-hour charges. Underlying AWS infrastructure fees may still apply separately depending on your setup.
The two dimensions bill independently. Each instance meters its own host hours at its own rate. Running both means both sets of host-hour charges appear on the same invoice, added together. Your total scales with how many hours each instance runs.
cohere.ai
Helpful?
Vendor refund policy
No refunds. Please contact support+aws@cohere.com for further assistance.
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
We've updated our SageMaker integration with a major version release for Embed and Rerank models, including notebook updates. The "/invocation" endpoint now defaults to API V2, ensuring a seamless transition to the latest version. Please see the notebook on how to use this model with the API update: a. All existing (and future) Embed models: https://github.com/cohere-ai/cohere-aws/blob/main/notebooks/sagemaker/Embed%20Models.ipynb b. All existing (and future) Rerank models: https://github.com/cohere-ai/cohere-aws/blob/main/notebooks/sagemaker/Rerank%20Models.ipynb c. All existing (and future) Command models: https://github.com/cohere-ai/cohere-aws/blob/main/notebooks/sagemaker/Command%20Models.ipynb
Additional details
Inputs
- Summary
The model accepts JSON requests with parameters that can be used to control the generated text. See examples and fields descriptions below.
- Input MIME type
- application/json
https://github.com/cohere-ai/cohere-developer-experience/blob/main/notebooks/sagemaker/Command%20Models.ipynb
https://github.com/cohere-ai/cohere-developer-experience/blob/main/notebooks/sagemaker/Command%20Models.ipynb
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
message | Text input for the model to respond to.
| Type: FreeText
| Yes |
chat_history | chat_history – (array of messages) A list of previous messages between the user and the model, meant to give the model conversational context for responding to the user's message. Required fields: role – (enum string) Takes “USER” or “CHATBOT”. message – (string) Text contents of the message.
| Default value: [] Type: FreeText
| No |
documents | A list of texts that the model can cite to generate a more accurate reply. Each document is a string-string dictionary. The resulting generation will include citations that reference some of these documents. It is recommended to keep the total word count of the strings in the dictionary to under 300 words. An `_excludes` field (array of strings) can be optionally supplied to omit some key-value pairs from being shown to the model.
| Default value: [] Type: FreeText
| No |
search_queries_only | When `true`, the response will only contain a list of generated search queries, but no search will take place, and no reply from the model to the user's `message` will be generated.
| Default value: FALSE Type: Categorical Allowed values: TRUE, FALSE
| No |
preamble | Overrides the default preamble for search query generation. Has no effect on tool use generations.
| Default value: [] Type: FreeText
| No |
stream | When `true`, the response will be a JSON stream of events. The final event will contain the complete response, and will have an `event_type` of `"stream-end"`. Streaming is beneficial for user interfaces that render the contents of the response piece by piece, as it gets generated.
| Default value: FALSE Type: Categorical Allowed values: TRUE, FALSE
| No |
max_tokens | The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations.
| Default value: [] Type: Integer Minimum: 0
| No |
temperature | Use a lower value to decrease randomness in the response. Randomness can be further maximized by increasing the value of the `p` parameter.
| Default value: 0.3 Type: Continuous Minimum: 0 Maximum: 2
| No |
Top P (p) | Use a lower value to ignore less probable options. Set to 0 or 1.0 to disable. If both p and k are enabled, p acts after k.
| Default value: 0.75 Type: Continuous Minimum: 0.01 Maximum: 0.99
| No |
Top K (k) | Specify the number of token choices the model uses to generate the next token. If both p and k are enabled, p acts after k.
| Default value: 0 Type: Continuous Minimum: 0 Maximum: 500
| No |
Resources
Vendor resources
Support
Vendor support
Contact us at support+aws@cohere.com
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
Command R+ 08-2024 is a highly performant generative language model optimized for large scale production workloads.
Command R is a generative language model optimized for long-context tasks and large scale production workloads.
Command A is a highly efficient generative model that excels at agentic and multilingual use cases.
Command R+ is a generative language model optimized for long-context tasks and large scale production workloads.
Command R+ is a generative language model optimized for long-context tasks and large scale production workloads.
Command R is a generative language model optimized for long-context tasks and large scale production workloads.
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.