Loading AI Digest
Bite-sized AI for curious minds...
Bite-sized AI for curious minds...
Pre-request token cost estimation for LLM APIs
Slash-tokens is a lightweight **WASM** module and SDK that was recently introduced via Show HN to estimate the token count of an LLM API call before it is sent. It enables developers to intercept high-cost calls, switch to cheaper models, or enforce per-user budgets while remaining provider-agnostic. With MIT licensing and CLI/SDK integration (e.g., via `bunx` or npm), it offers a small but critical building block for cost-aware AI applications.