Skip to content

Welcome to Litmus

Define test cases, run them against LLM models via OpenRouter, and compare accuracy, latency, and throughput across models.

Define Test Cases

Create test cases with input strings and expected JSON outputs in a simple JSON format.

Compare Models

Test against multiple LLM models via OpenRouter and compare their performance side by side.

Measure Performance

Track accuracy, latency percentiles (P50, P95, P99), and throughput (tokens/second).

Multiple Output Formats

Generate reports in terminal, JSON for CI/CD, or self-contained HTML for sharing.