L

llm-cost

Terminal dashboard for LLM spend: feed it a log of your model calls and see cost per request, cost per model, budget used and a projected monthly bill, priced from a built-in table of 83 models. Runs locally, no account.

GitLab CI/CD components for LLM apps: fail the pipeline on likely hallucinations, prompts over their token budget, padded prompts, an LLM bill heading over budget, or slow and flaky models. Tested on every push.

Single-header C++17: token counts and dollar cost estimates for OpenAI and Anthropic models before you send, with budget checks. Part of llm-cpp.

Hard budget enforcement for LLM agent fleets: track token spend per model, agent and fleet, and block requests before they exceed a limit. Rust.