Evanesca is now on Android 📱
A Private European AI Assistant where your data never leaves Europe, and your chats never leave your phone.
Same European guarantees:
- All 19 models run in Europe, by European operators
- No training on your chats
- Nothing kept after the answer
- Every answer comes with a "passport": where it was processed, and what we kept (nothing)
All the tools, built with European partners:
- Web search via Linkup 🇫🇷
- Images by Infomaniak 🇨🇭
- Dictation by Mistral AI 🇫🇷
- Photos & scans: GPS and device data stripped
- PDF, Word, Excel: read and written
- Memory: optional, kept on your phone
Your chats stay on your device:
- Stored on the phone, no copy on our servers
- Hidden in the app switcher by default
- Fingerprint or face lock if you want it
Android 7+, available now on Google Play.
19 models on Evanesca. Which one to pick?
You don't have to. Auto picks the right model for each message: good enough for the task, then the cheapest.
🇪🇺 Only models running in Europe
🔍 Model named on every answer
💸 No routing fee
Try Auto → evanesca.app
Tired of watching your AI credits run out? 👀
With Evanesca, you choose how to pay:
💳 Pay as you go — top up whenever you need.
🔄 Subscription — get more credits every month.
🚀 Up to +15% bonus credits.
🔓 No commitment. Cancel anytime. Your credits never expire.
AI on your terms. No surprises.
Discover Evanesca 👉 evanesca.app
#AI #Privacy #PrivateAI #Evanesca #EuropeanAI
9
72
Pretty useful !
Kimi K3.1 Pro or GLM-5.3?
The only fair way to decide is to test them on your own prompts before you integrate anything.
New in the Frontière AI: Compare mode.
You send one prompt to two models at the same time and read their answers side by side as they arrive.
Under each answer you get the tokens used, the cost, the time to first token, the total time and the throughput.
In the video, we ask both models for a Python function that removes duplicates from a list while keeping the order.
→ GLM-5.3 sends its first token sooner (0.48 s) and generates more tokens per second (108 tok/s).
→ Kimi K3.1 Pro still finishes in 5.2 s instead of 11.1 s, and costs €0.0070 instead of €0.0111.
The reason is that GLM-5.3 reasons first (730 tokens) and generates 1,162 tokens in total, against 442 for Kimi. The fastest model per token isn’t always the cheapest per answer.
To keep the comparison fair, we set 4 rules:
- Same settings on both sides: system prompt, temperature, max tokens and top-p.
- Web search and tools are off, so you compare the models and not their tools.
- No winner by network luck: when the gap is under 5%, no star is awarded.
- Measured the way your app sees it: in your browser, with network and gateway time included.
Billed like the API: each answer is charged at its model’s per-token price. If you stop an answer midway, the part that wasn’t generated isn’t billed.
Then you pick the best model and wire it up in one line. Your app uses the same gateway, the same route and the same per-token price, so it gets exactly what you measured.
Your comparisons stay in your browser and never reach our servers.
Quality, speed, price: compare before you wire up the API.
#SovereignAI #LLM #OpenWeight #API #Developers #FrontiereAI
7
130
New on Evanesca: Gemma 4 26B by Google 🇪🇺
Google’s open model, run in Germany, not on Google’s servers.
Apache-2.0, 256k context, text + images.
6/6 checks passed. Your photos and chats: not kept, not used for training.
Try it → evanesca.app
New on Evanesca: @apertusllm v1.5 70B by the Swiss AI Initiative (EPFL, ETH Zurich) 🇨🇭
Runs in Switzerland.
Apache-2.0, open weights.
Text + images.
5/6 checks passed. The one it failed: security (3/5) because of system prompt leaking.
Try it → evanesca.app
10
115
A frontier model, now run in Germany. 🇪🇺
Kimi K3.1 Pro is live on Evanesca as of today.
Moonshot AI built it in China and released it as open weights. Because the weights are open, we can run it ourselves on GPUs in Germany.
Your conversations NEVER need to leave Europe to reach one of the most capable models of the moment.
What that means for your team:
→ No training on your chats
→ No permanent copy of your conversations
→ Served in Germany, in line with GDPR
Before any model goes live on Evanesca, it has to pass 6 checks: licence, provenance, security, GDPR, benchmarks and a live test.
Kimi K3.1 Pro passed all 6, including all 5 attack categories in our security audit.
Under the hood:
2.8T parameters (104B active per token)
1M-token context
Tools + reasoning, text and image input
It’s in your model picker today, alongside DeepSeek, Mistral, GLM and Qwen.
Using frontier AI no longer means trading away your data.
#AI #DataPrivacy #GDPR #DigitalSovereignty #EuropeanTech #GenAI
1
10
177
Where does your data go when an AI agent reads your files? 🇪🇺
With Evanesca, nowhere you can't see:
📍 The model runs in Paris, Germany, and other places in Europe
💻 Your files stay in your browser, not on our servers
🚫 Your data is never used for training
In the demo: 3 supplier quotes in, an Excel comparison and a memo out. 14 seconds, €0.07. It even caught a €4,800 exit fee 👀
A European AI agent. Your data stays yours.
evanesca.app
#AI #DataSovereignty #Privacy #GDPR #Europe #EuropeanTech #AIAgent #TechTok
Evanesca is live on PH !! 🔽
producthunt.com/products/eva…
Go upvote our European Private AI Chat & Agent if you believe in Sovereign and open-weight AI
9
87
New on Evanesca - Your Private European AI Chat
Kolibri 1 by @Aleph__Alpha 🇩🇪
Made in Germany. Runs in Germany. Apache-2.0, open weights.
78B, 256k context, tools + reasoning.
6/6 checks passed before going live. What we keep from your chats: NOTHING.
Try it today → evanesca.app
Does your AI tell you where its answer came from?
Evanesca does. Every answer comes with a passport: which model, where it ran, what was kept (nothing), whether it trains on your data (no), and what it cost.
18 models. All in Europe.
evanesca.app 🇪🇺
Your chats stay in your browser. Evanesca keeps no copy.
Web search is off by default. You switch it on when you need it, and even the web search is sovereign thanks to linkup's agent browser + every source is cited.
In the demo: a question about the EU Data Act, a sourced answer as a table, then a live page built by the model. Cost: €0.0094.
14
Mistral is now 6/6 on our benchmarks and tests!
Open-weight = no black box, no lock-in, no data leaving Europe.
That’s why it’s now available on Evanesca 🇪🇺
Private AI, built for people who care where their data goes.
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
🇪🇺 Built in Europe. For Europe.
"We'd love to use AI… but IT blocked it."
So we built Evanesca: a private AI chat and agent where every answer is processed in Europe, and nothing is kept once it's written.
In 1 minute:
→ 18 open models (Mistral, DeepSeek, Qwen, Apertus…), all run in Europe
→ Board-ready charts, live calculators, GDPR checklists
→ A passport on every answer: model, host, country, training, cost (€0.0011)
No copy. No training on your data. Pay as you go.
We answer. Then we forget.
Send this to your CIO.




