The complete inventory of all providers, models, APIs, and tools powering the Ensoria ecosystem — from cloud AI models to local inference, infrastructure, and membership plans.
The primary and fallback models available via cloud providers, routed intelligently by the Ensoria Router.
| Model | Provider | Usage | Cost |
|---|---|---|---|
| DeepSeek V4 Flash | DeepSeek | Primary model — main session agent | Included (subscription) |
| DeepSeek V4 Pro | DeepSeek | Complex reasoning, deep analysis | Included (subscription) |
| OpenAI GPT-4o | OpenAI | Enterprise-grade reasoning, fallback | €5–15/mo (API usage) |
| OpenAI GPT-4o Mini | OpenAI | Fast, lightweight tasks | €2–5/mo (API usage) |
| OpenAI GPT-4.1 series | OpenAI | Latest GPT-4 generation | €10–25/mo (API usage) |
| Google Gemini 2.5 Flash | Fast inference, cost-efficient | Free tier + €5/mo | |
| Google Gemini 2.5 Pro | Complex multimodal reasoning | €10–20/mo | |
| Google Gemini 3.1 Flash Image | Image analysis & generation | Free tier + €3/mo | |
| Perplexity Sonar | Perplexity | Web search, fact retrieval | Free tier + €5/mo |
| Perplexity Sonar Pro | Perplexity | Advanced search with citations | €10/mo |
| Perplexity Reasoning Pro | Perplexity | Multi-step reasoning + deep search | €15/mo |
| Perplexity Deep Research | Perplexity | In-depth research reports | €20/mo |
| OpenRouter | OpenRouter | Aggregator — hundreds of models | Pay-as-you-go API |
On-device inference via Ollama on the M5 machine with 64GB RAM. Zero latency, zero API cost, full privacy.
| Model | Size | Quantization | RAM Usage |
|---|---|---|---|
| Qwen 2.5 72B | 47 GB | Q4_K_M | ~28 GB |
| Qwen 2.5 32B | 19 GB | Q4_K_M | ~16 GB |
| Gemma 3 27B | 17 GB | Q4_K_M | ~14 GB |
All models run on M5 machine with 64 GB RAM via Ollama. Switchable on demand by Ensoria Router.
Every external service and API that Ensoria connects to, extending its capabilities beyond the model layer.
Gmail, Drive, Contacts — OAuth 2.0 authenticated. Read & write access for email management, document retrieval, and contact synchronization.
DNS management, Cloudflare Tunnel (4 QUIC replicas) for secure ingress without open ports.
24 tools, 3 resources. The Model Context Protocol bridge connecting Ensoria to external systems, databases, and services.
OpenAI Whisper running locally via CLI. Zero API key required. Full privacy for voice transcripts.
Powered by Google Gemini. Analyze images, screenshots, diagrams, and visual content in conversations.
Powered by Google Gemini. Generate images from prompts directly within Ensoria.
Powered by Google Veo. Generate short video clips from text descriptions.
Powered by Google Lyria. Generate original music tracks from prompts.
Text-to-speech for voice output. Supports multiple voices and languages.
Powered by Perplexity and Google. Real-time web search integrated into Ensoria's reasoning flow.
Extract readable content (HTML → markdown/text) from any URL. Lightweight page access without browser automation.
The physical and virtual infrastructure that hosts Ensoria, from cloud VPS to network protocols.
Specs: 16 vCPU · 30 GB RAM · 610 GB NVMe + 1 TB HDD
Hosts the Ensoria Mother Node, back-end services, and persistent storage.
4 QUIC replicas
Zero-trust ingress, no open ports, DDoS protection, automatic failover.
Distributed Neural Agent Network — P2P encrypted mesh for multi-node Ensoria deployments. Each peer is a sovereign agent node.
Main session runs on AleX's Mac M5. Orchestrates all agents, tools, and model routing. Local inference via Ollama.
Every module that makes up the Ensoria OS — from the chat agent to the management platform.
The main chat agent. Available on Telegram, WhatsApp, Signal, Discord, and WebChat. Your primary interaction point with Ensoria.
Full-stack management platform: CRM, Projects, Events, Requirements, Milestones. Web UI + REST API.
Brain (operational framework), Soul (values & principles), Router (model routing intelligence). The foundation of every Ensoria instance.
Website chat widget for live customer interactions. Embeddable in any site.
24 tools, 3 resources. The Model Context Protocol bridge connecting Ensoria to external systems and data sources.
Every resource mapped to the four membership tiers. Choose the plan that matches your needs.
| Resource | Personal | Professional | Startup | Enterprise |
|---|---|---|---|---|
| AI Cloud Models | DeepSeek + Gemini | DeepSeek + Gemini + GPT | DeepSeek + Gemini + GPT + Perplexity | Full access + OpenAI |
| AI Local Models | ❌ | ✅ Qwen 32B | ✅ Qwen 72B | ✅ Full local + custom |
| Image Analysis | ✅ Gemini | ✅ Gemini | ✅ Gemini | ✅ Gemini |
| Image Generation | ✅ Gemini | ✅ Gemini | ✅ Gemini | ✅ Gemini + custom |
| Video Generation | ❌ | ❌ | ✅ Veo | ✅ Veo + custom |
| Music Generation | ❌ | ❌ | ❌ | ✅ Lyria |
| Google Workspace | ✅ | ✅ | ✅ | ✅ |
| MCP Server | ❌ | ✅ (basic) | ✅ (full) | ✅ (full + custom) |
| Local Models | ❌ | ✅ (32B) | ✅ (72B) | ✅ (full suite) |
| VPS | CX32 (16GB) | CX42 (32GB) | CX52 (64GB) | Custom |
| Storage | 100 GB | 250 GB | 500 GB | Custom |
| Users | 1 | 1 | Up to 3 | Unlimited |
| Channels | Telegram + WebChat | + Signal | + Discord + API | |
| DNAN Node | ❌ | ❌ | ✅ Child Node | ✅ Full mesh |
| Support | Community | Priority | Premium | Dedicated |
| Price | €20/mo | €49/mo | €99/mo | Custom |
Estimated return on investment based on hours saved and typical professional billing rates.
| Plan | Cost/mo | Hours saved/mo | Value at €25/h | Net ROI |
|---|---|---|---|---|
| Personal | €20 | ~20 h | €500 | +€480/mo |
| Professional | €49 | ~40 h | €1,000 | +€951/mo |
| Startup | €99 | ~80 h | €2,000 | +€1,901/mo |
| Enterprise | Custom | ~160+ h | €4,000+ | Custom |
* Estimated at €25/h. Real ROI depends on your specific use case. For professionals billing €50–100/h, the ROI doubles or more.