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.

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:

Create an account at app.notdiamond.ai
Create a Not Diamond API key
Jump into the quickstart example

Alternatively, you can try chatting with our Not Diamond-powered chatbot to see what routing feels like as an end-user. We also have a Not Diamond-powered RAG app that you can use to ask any questions you have about Not Diamond.