Local LLM Server Pro vs Openrouter Tracker

Turn Apple Intelligence into a local API for your scripts and apps. Local LLM Server Pro exposes Apple's on-device language model through selected OpenAI and Ollama-compatible endpoints. Inference stays on your device. PRO: A ONE-TIME PURCHASE No ads and no daily generation request quota. Pro does not expand Apple's model context window or guarantee background service. The free version is ad-supported and allows 100 generation requests per day. START WITH ONE RESPONSE Enable Apple Intelligence and wait for the model to be ready. Start the server, open the in-app playground, and ask a short question. Then use the curl, Python or JavaScript examples in Server Information to connect your client. A step-by-step setup guide is available from the support link. SUPPORTED WORKFLOWS • OpenAI Chat Completions with a custom /v1 base URL, streaming, structured output and tool-call responses. • Selected Ollama chat, generate and model-list endpoints. • Text embeddings using Apple's contextual embedding provider. • Same-device localhost access, or local-network access with an optional API key. • Server logs, request statistics and Shortcuts for server controls. KNOW THE LIMITS This app uses Apple's supported on-device model. It does not import GGUF or Hugging Face models, download arbitrary Ollama models, or provide OpenAI's Responses API. Use model IDs returned by the server, such as base. Compatibility depends on the endpoints your client uses. Requests can contain up to 1 MiB of JSON. This HTTP byte limit is separate from the model's token context. Shorten large conversations or tool definitions; use max_tokens to bound replies. KEEP THE SERVER VISIBLE Keep the app in the foreground while serving. On iPad, use Split View with your client alongside it. Requests may pause when the app is backgrounded or the screen locks. The optional background reminder is advisory, not suspension detection. REQUIREMENTS Apple Intelligence-capable hardware with iOS/iPadOS 26 or later, or macOS 26 or later on a compatible Apple silicon Mac. Apple Intelligence must be enabled, supported in your language and region, and its on-device model ready. Setup may require a model download. Setup and troubleshooting: https://www.kevintang.xyz/apps/Local-LLM-Server-Pro/support.html

Stop opening the OpenRouter dashboard. See credits, spend, tokens, and API keys on iPhone—with Home Screen widgets you check in seconds. Who it’s for Built for developers and power users who route LLM traffic through OpenRouter—whether you call models from your own apps, OpenCode, Hermes, Cursor-style agents, or any stack that burns API credits in the background. Problems we solve • Surprise spend — credits drop while agents run; you only notice when something fails • Dashboard friction — checking usage means opening Safari, logging in, and digging through the web UI on a phone • Per-key blind spots — multiple API keys (prod, dev, agents) with no quick view of limits and remaining balance • Model mix mystery — hard to see which models drive cost without charts • No glanceable monitor — nothing on your Home Screen until now How much time you save • ~5–15 seconds → under 2 seconds for a credits check via the small widget • Skip the browser entirely for daily spend, request counts, and token totals • One pull-to-refresh instead of reloading the OpenRouter dashboard across tabs • Spot spikes from Home Screen with the 30-day heatmap before opening the app Features Overview • Remaining credits, spend, requests, and tokens • latest / 7 / 30 day periods • Usage pace: active streak, daily average, weekly average • Tap through to activity log and top models Three Home Screen widgets • Openrouter Tracker — credits + 7-day spend, requests, tokens (small / medium / large) • Activity heatmap — 30-day grid; switch spend, requests, or tokens • Daily chart — 7-day stacked bars by top model; pick your metric API keys • Per-key usage and remaining limit when set • Stacked daily charts for spend, requests, and tokens • Top models per key Privacy & data • Your management API key stays in the Keychain on device • Widgets read cached aggregates only — your key never runs inside the extension • Direct OpenRouter REST calls; no custom backend Localized in 31 languages The app UI and widgets follow your language setting: English · Español · Français · Deutsch · Italiano · Português (Brasil) · Português (Portugal) · Nederlands · Русский · 日本語 · 한국어 · 简体中文 · 繁體中文 · العربية · हिन्दी · Türkçe · Polski · Bahasa Indonesia · Tiếng Việt · ไทย · Svenska · Dansk · Norsk · Suomi · Čeština · Українська · Ελληνικά · עברית · Română · Magyar · Bahasa Melayu Change language in Settings, or follow your iPhone system language. Get started Add your OpenRouter management API key once. Pull to refresh after agent runs. Add widgets to your Home Screen and stop babysitting the dashboard.