Technical guides
TokenHawk technical guides on LLM token optimization: semantic caching, cost breakdown, multi-turn agents.
Tuning a semantic cache for an LLM proxy
How a semantic cache decides a new question is close enough to an old one to reuse its answer — and why the similarity threshold is the real lever.
Why a single per-token price lies on your bill
The token count a provider bills isn't a flat rate: cache reads, cache writes and reasoning each carry their own price. Skipping the breakdown overbills some usage by a factor of 10.
Multi-turn agents: where the tokens actually go
A ReAct agent looping over tool calls sees its context grow every turn. Without history compression, a 10-turn agent's cost grows quadratically, not linearly.