I built react-native-llm-meter, LLM cost tracking for Expo apps
Ankit Virdi developed react-native-llm-meter, a library for tracking LLM usage and costs directly within Expo and React Native applications. The tool supports on-device monitoring of token counts, latency, time to first token, and cost calculations without accessing prompt content. It integrates with popular LLM providers and offers local storage, budget alerts, and a development overlay for real-time metrics.
- ▪react-native-llm-meter is designed for React Native and Expo apps making direct LLM calls from devices.
- ▪The library supports Anthropic, OpenAI, and Google's Gemini with AsyncStorage and SQLite storage adapters.
- ▪It captures metrics like token usage, latency, time to first token, and computes costs while preserving user privacy by not logging prompts.
- ▪Streaming time to first token (TTFT) is measured separately from total latency to reflect user-perceived responsiveness.
- ▪Budget alerts are supported, with plans for circuit-breaking functionality in future updates.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3908228) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Ankit Virdi Posted on May 1 I built react-native-llm-meter, LLM cost tracking for Expo apps #reactnative #llm #ai #typescript If you ship Claude, GPT, or Gemini calls from a React Native app, you have a problem nobody's solved well, you don't know what's happening on the device. Server-side observability is excellent. Langfuse, Helicone, LangSmith, Stripe's token-meter all work amazingly for Node backends.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
