Not Diamond is an AI model router that automatically determines which LLM is best-suited to respond to any query, improving LLM output quality by combining multiple LLMs into a meta-model that learns when to call each LLM.
Not Diamond intelligently identifies which LLM is best-suited to respond to any given query by combining multiple LLMs into a meta-model that learns when to call each LLM.
Key features
Maximize output quality: Not Diamond outperforms every foundation model on major evaluation benchmarks by always calling the best model for every prompt.
Reduce cost and latency: Make intelligent cost and latency tradeoffs to efficiently leverage smaller and cheaper models without degrading quality.
Personalized routing with feedback: Hyper-personalize routing to each individual end user in real-time based on their feedback.
Train your own custom router: Leverage your evaluation data to train your own custom routers optimized to your use case.
Not a proxy: Receive recommendations for which LLM to use and then make your LLM requests client-side in whatever way you choose.
Python, TypeScript, and REST API support: Easily integrate Not Diamond across a variety of stacks.
Getting started
Making your first API request with Not Diamond takes less than 5 minutes. To get started:
Alternatively, you can try chatting with our Not Diamond-powered chatbot (https://chat.notdiamond.ai) to see what routing feels like as an end-user. We also have a Not Diamond-powered RAG app (https://rag.notdiamond.ai/) that you can use to ask any questions you have about Not Diamond.
Highlights
Maximize output quality: Not Diamond outperforms every foundation model on major evaluation benchmarks by always calling the best model for every prompt. You can also leverage your own evaluation data to train your own custom routers optimized to your use case.
Reduce cost and latency: Make intelligent cost and latency tradeoffs to efficiently leverage smaller and cheaper models without degrading quality.
Not a proxy: Receive recommendations for which LLM to use and then make your LLM requests client-side using your preferred method, such as AWS Bedrock.
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 is based on the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Free up to 100k monthly API routing requests. Train one custom router. Intelligent cost and latency tradeoffs. Joint prompt optimization support. Fallback rerouting.
$0.00
-
Possibility
Everything in Discovery plus $0.001 per API routing request after the first 100K free. Uncapped API routing requests. Unlimited custom routers. Enhanced data privacy with fuzzy hashing.
$100.00
$0.001/unit
Necessity
Everything in Possibility. VPC deployments. Custom integration and router training support. Access and permissions management. We will reach out to set this up for you.
You choose from three tiers that build on each other. Discovery is the free entry point. It covers routing requests up to a monthly limit and lets you train one custom router. Possibility includes everything in Discovery, then charges per routing request beyond the free monthly amount. It removes the request cap and allows unlimited custom routers. Necessity includes everything in Possibility and adds deployment inside your own private network, custom integration support, and access controls. The vendor sets up Necessity directly with you. Pricing scales with routing request volume and the level of deployment and support you need.
Top-of-mind questions for buyers
What counts as one API routing request for billing on the Possibility tier?
Each API request returns one routing recommendation, no matter how large the input. The router looks at your prompt and candidate models, then recommends which model to use. One request equals one recommendation. Beyond the first 100K free monthly requests, each additional request accrues a per-request charge.
What happens to my cost if I exceed the 100K free monthly routing requests?
On Discovery, routing requests are free up to 100K per month, and that is the cap. On Possibility, the cap is removed. Requests beyond the first 100K free each month accrue a per-request charge. Only the requests above 100K are billed, not all of them.
What extra capabilities does Necessity add beyond routing request volume?
Necessity includes everything in Possibility, then adds deployment inside your own private network, custom integration and router training support, plus access and permissions management. Cost reflects deployment and support needs, not just request volume. The vendor reaches out to set this up directly with you.
www.notdiamond.ai
Helpful?
Vendor refund policy
All Orders are non-cancellable and all fees and other amounts you pay under this Agreement are non-refundable.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
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.
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.