⚡
Latency probe
Measures real time-to-first-token with streaming requests. Best, median and worst across N runs.
💰
Pricing catalog
Fetches a provider's /v1/models catalog with per-million token prices and discounts.
📦
Zero dependencies
Pure Python standard library. Clone and run — nothing to install.
🔒
Wallet-safe
Probes send max_tokens=1 and warn before spending anything.
Quick start
# clone and configure git clone https://github.com/frost13ru-svg/ai-cost-monitor.git cd ai-cost-monitor && cp .env.example .env # benchmark a model (near-zero cost) ./run.sh probe --model gpt-6-luna --runs 3
💡 Want these prices too?
This project runs against Cheaper Inference — an OpenAI-compatible marketplace with up to 80% off list prices across OpenAI, Anthropic, DeepSeek, Z.ai and more. Fund from $5, no monthly commitment.
Sign up with our referral link ❤ Support the project