Ollama Router Pro: LLM Gateway

Ollama Router Pro is a lightweight, on-device AI proxy server and intelligent model router designed for developers, engineers, and creators. Host your own local OpenAI-compatible gateway right on your Android phone and route queries from coding assistants, IDEs, and developer tools across configurable model tiers.

Whether you run local models with Ollama on your home network or connect cloud API keys (DeepSeek, OpenAI, Anthropic, Google Gemini, Groq), Ollama Router Pro inspects prompt complexity and routes each request to the most cost-effective and capable model.

### Why Use Ollama Router Pro?

Every prompt has different requirements. Simple coding syntax or quick questions do not require expensive frontier models, while complex system architectures and deep debugging demand high reasoning depth. Ollama Router Pro balances speed, quality, and cost automatically:

• ⚡ Simple & Fast Tier: Handles formatting, basic translations, regex, and short lookups using fast, low-cost models (Ollama local, DeepSeek Chat, GPT-4o Mini, Claude 3.5 Haiku, Gemini 2.0 Flash).
• 🧠 Balanced Work Tier: Directs multi-file refactoring, code review, and general programming tasks to top-performing development models (Claude 3.5 Sonnet, GPT-4o, Gemini 1.5 Pro).
• 🔬 Deep Analysis & Reasoning Tier: Reserves frontier reasoning models (DeepSeek R1, OpenAI o1/o3, Claude Opus) for architectural planning, algorithmic edge cases, and complex mathematics.

---

### Key Features

• 1-Click Local Proxy Server: Runs an HTTP proxy directly on your Android device (:18800). Connect your laptop, PC, or desktop via USB ADB or your local Wi-Fi network.
• Seamless Developer Tool Compatibility: Drop-in replacement for Cursor, Claude Code, Cline, Roo Code, Continue.dev, and standard OpenAI / Anthropic SDK clients.
• Local Ollama & Custom Provider Support: Easily add your local Ollama instance (e.g., http://192.168.x.x:11434/v1) or any custom OpenAI-compatible endpoint.
• Automatic Fallback Chains: Protect your workflow from rate limits (HTTP 429) or server outages by automatically cascading to configured backup providers.
• Real-Time Savings & Usage Analytics: Monitor request volume, token savings, response latency, and tier routing distributions directly from the dashboard.
• Built-In AI Chat Playground: Test model connections, explore response speeds, and experiment with prompt routing using rich Markdown rendering and voice dictation.
• Token Saver & Optimization: Optional RTK compression losslessly strips git diff and log fluff to reduce input tokens by 20–40%.
• Encrypted On-Device Security: Private API keys are stored locally using Android Keystore hardware-backed encryption (AES-256-GCM). No intermediate cloud server ever sees your keys or prompts.

---

### Quick Setup Guide (60 Seconds)

1. Open Ollama Router Pro on your device and turn on the router switch.
2. In the Keys tab, add your preferred provider access keys or link your local Ollama server IP.
3. In your editor (Cursor, Claude Code, Cline, or Continue), set:
- Base URL: http://:18800/v1 (or http://127.0.0.1:18800/v1 via ADB reverse)
- API Key: ollama-router
- Model: freerouter/auto (or choose specific tiers)
4. Start coding and watch your queries route seamlessly in real time!

---

### Privacy & Security First

Ollama Router Pro operates strictly as an on-device local proxy. It does not run external cloud relays, does not harvest prompts, and does not profile users. All communications go directly from your local network to your chosen providers.

---

### Trademark Disclaimer
*All product names, logos, and brands (including Ollama, OpenAI, ChatGPT, Anthropic, Claude, Cursor, DeepSeek, Google Gemini, Groq) are property of their respective owners. Their mention in this listing is solely for technical compatibility identification and nominative fair use.*