Overview
KeyInspect AI is a client-side API playground and telemetry tester for large language models. It is designed for developers, researchers, and AI enthusiasts to test LLM endpoints, benchmark streaming speeds, and organize prompts without a middleman server or paid subscription.
The tool provides real-time telemetry tracking TTFT, TPS, and total generation duration. It natively supports OpenAI, Anthropic, Google Gemini, DeepSeek, OpenRouter, and Groq, and connects to local inference servers like Ollama and LM Studio.
It includes a custom template builder for undocumented APIs, per-chat isolated parameters, a smart CORS proxy, and zero server storage. API keys and chat history are stored locally in the browser's localStorage.
It requires zero installation or build steps, built with vanilla web technologies. Users can serve locally with npx serve, use Live Server, or double-click index.html. It makes direct requests from the browser to endpoints, with no telemetry or analytics collected.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Developers use KeyInspect AI to test LLM endpoints without a middleman server.
- Developers use KeyInspect AI to benchmark streaming speeds with real-time telemetry.
- Developers use KeyInspect AI to connect to local inference servers like Ollama and LM Studio.
- Developers use KeyInspect AI to build custom templates for undocumented APIs.
- Developers use KeyInspect AI to maintain isolated parameters per chat session.
- Developers use KeyInspect AI to bypass CORS policies on public APIs.
Features
Runs as a client side playground
Tests large language model endpoints
Inspects LLM API telemetry
Benchmarks streaming response speeds
Supports API testing without dependencies
Reviews
No reviews yet. Be the first to share your experience!