Stop overpaying for LLM calls by defaulting to flagship models. We ran 7,560 tests across 18 models (OpenAI, Anthropic, Google, Mistral) and found that mid-tier models often match state-of-the-art accuracy at 1/10th the cost. Arbitr lets you audit your own documents against 18+ LLMs side-by-side. Compare accuracy, cost, and reliability in real-time to find your perfect model fit. - Side-by-side OCR audit - Cost-per-success metrics - Open-source benchmark framework