Not Diamond — new SOTA meta-model

[t5-notdiamond]

Hey HN, glad to see this here—I’m the founder and CEO of Not Diamond. Not Diamond makes it super easy to train your own custom AI model routers on your data to outperform any single model by intelligently routing to the highest-quality model for each query. We beat every foundation model on every major benchmark at a lower cost and latency.

To train a router, you literally just upload a dataset with your inputs and eval scores for different models. It’s completely agnostic to your choice of scoring metrics, frameworks, or tools. And if you don’t have your own eval data, you can still use Not Diamond’s base router out of the box—it takes <5m to set up.

Some other features worth noting:

• Python, TypeScript, and REST API support

• Option to route to faster/cheaper models when doing so doesn’t impact quality

• Joint prompt optimization interface

• Online, real-time personalization to hyperpersonalize model recommendations to individual end users

• Blazing fast inference speeds (<100ms)

• Easy deployments to your private infra

Would love to hear what folks think.

[tbarn]

I've been working with the team at Not Diamond and trying out the private beta for a couple of weeks, and the routing experience is great. It makes it really easy to use different models and also route based on different tradeoffs. All I had to do was grab API keys from the different LLM APIs and quickly set it up.

[t5-notdiamond]

Thank you—really glad we could work together on this

[ramly]

Super cool to see this on HN. Saw Tomas demo an early version of it last year. Very neat work and the team behind it is brilliant.

[t5-notdiamond]

Thanks Sami :) Has been awesome to be able to share our progress with you

[tt2114]

Very nice, exactly what I have been looking for. Sign up was easy as well and I have it working in my personal project already.

[t5-notdiamond]

Glad to hear that

[randyzwitch]

Are computer vision models supported?

[t5-notdiamond]

Not yet—very much on the roadmap though

[drewfustin]

Looking into it

[t5-notdiamond]

Awesome, lmk what you think

[pinkbeanz]

this is neat, where can i find more details on how the automatic routing logic works?

[t5-notdiamond]

Hey, thanks for checking it out! You can find some more info on how Not Diamond works here: https://notdiamond.readme.io/docs/how-not-diamond-works