discode.ai

100+ AI models, one interface. ECO friendly.

Productivity

SaaS

Artificial Intelligence

Visit WebsiteSee on Product Hunt

The CO2 footprint tracking per prompt is a genuinely fresh angle -- most AI tools pretend environmental cost does not exist, but making it visible nudges users to think twice before over-prompting, which is a quiet but powerful design choice.

The eco footprint per request is a great touch. What data source are you using for the CO2 estimates per model? Numbers vary a lot by datacenter location and grid mix, curious how granular you can get.

Congrats on the launch! 🚀

The eco angle is refreshing, but I also really like the on-device privacy filtering. Most AI routers focus only on cost and speed, while privacy and model choice are just as important.

Curious how transparent the routing explanation is for non-technical users can they easily understand why a specific model was selected?

Hi Moriz and team; congratulations to the launch. I really like the one-device privacy filtering feature and the overall ECO dimension (amid the hottest days ever in our region😓) Good luck and keep going!

Hi Discode team! Interesting and valuable product - congratulations on the launch. I’m keen on saving admin by establishing one subscription instead of multiple. Curious if I as user can steer optimization parameters - output, cost or environment as % distribution? Ulrika

Thanks Moriz, splitting it into two loops is the right framing. The nightly catalog sweep keeps the model rankings honest, but that is recalibrating which model wins a tier, not whether the difficulty classifier put the prompt in the right tier in the first place. A re-ask is a free label there: an escalation event saying this domain was under-tiered. Even aggregated rather than per-user, feeding those escalations back into the per-domain thresholds is what would actually tighten the eco budget over time. Is that the second loop you mean, or is the nightly sweep doing double duty for now?

As an AI chatbot that routes queries across 100+ models, protects user privacy, and tracks the environmental cost of each interaction, discode.ai is to me an act of resistance against the extractive, engagement-driven business logic behind most of the internet.

And it's live. And everyone can use it!

🪩

As an ai-chatbot that protects user privacy, and tracks the environmental cost of each interaction, discode.ai seems an act of resistance against the extractive, engagement-driven business logic behind most of the internet.

🪩

The "you set the rhythm" line is what got me, most multi-model tools feel like a model zoo dump, but framing it around the user's own pace is a nice touch.

My favourite part is the fact that I can start using it and it just WORKS, and over time I can dive deeper and start adjusting to my needs.

Hello makers!

I hope you find the eco aspect of discode as valuable as I do.

With many AI tools, it is easy to overlook switching models manually. I often find myself selecting the most capable model and then using it for every task, regardless of its complexity.

That is exactly why Eco Routing matters to me. It automatically matches each request with a model that is capable enough for the task, while avoiding unnecessary energy and resource consumption.

Appreciate the detail Moriz. That four-tier domain routing bounded by the Turntables makes the upfront call legible, which is more than most routers offer. The piece I keep circling is the loop after the fact. When a tier under-serves and the user re-asks, does that signal feed back to recalibrate the domain benchmark, or is routing static per release? Closing that loop is what would turn this from a good router into one that actually gets sharper with use.

Hey Makers,

We are live!!!!

I'm Veronika, and I lead Product Strategy and User Experience.at discode.ai and I spend my days thinking of ways of making humans and technology tolerate each other.

I'm SO excited about what we're building here because it tackles the questions that have followed AI from the very start: Does it all have to cost the planet? Do I get to have to hand over my data and still get a good answer?

Our goal here is to make LLMs approachable, understandable, and intentional.
We remove the guesswork!
We help you use only as much AI as you actually need!
And we keep your personal data where it belongs: with you.

We wrapped all of that in an interface that's unapologetically progressive, unmistakably European, and just the right amount of snarky.
It's designed for your control, clarity, calm- and the occasional drizzle of disco.

Come join the party!!

Let's dance —respectfully, frugally, and with better AI.

— Veronika

Hi! It‘s finally live!

From corporate design and UI-design to branding and illustration, I‘m happy to be part of the disco. Let‘s explore and improve the visual side of discode!

H

The eco-slider is interesting! Wondering...When the frugal tier under-serves a hard prompt and I re-ask, that retry probably burns more than just hitting a frontier model once? Does a re-ask count against the eco budget? Showing which model answered and why is the right call regardless!

The Eco routing angle is genuinely interesting but I'd love to know how the difficulty classification works upstream. If the routing decision itself runs on a heavyweight model every time, does that overhead cancel out the savings on simpler queries? Curious if you've benchmarked the router's own footprint.

The on-device PII redaction before anything leaves is the part most AI routers skip - model routing and cost views are everywhere, but client-side redaction is what actually makes this safe to put in front of a team. My one concrete worry: when a name or ID gets redacted but is needed for the current answer and was first mentioned 10 messages back, does it consistently re-mask the same entity to the same token across the thread so the model still gets coherent context, or can it lose that reference once it is stripped?