Estimate token count for a text string. Uses calibrated chars/token ratios per model. Example: estimate_tokens(text='Hello world', model='gpt-4o') → {tokens: 2, ...}

Compress a prompt to reduce token usage. strategy: 'trim' (whitespace/blanks), 'summarize_hint' (mark long sections), 'aggressive' (strip comments, examples, filler). Returns compressed text + savings stats.

Recommend the cheapest capable model for a task. Filter by min_quality (1-10, default 7) and max_cost_per_1k USD. Returns ranked candidates with per-call cost estimate.

Look up a cached result by prompt text or pre-computed cache key. Returns {hit: true, result, tokens_saved} or {hit: false}.

Store a prompt+result in the cache. Provide prompt (auto-hashed), result text, tokens_saved estimate, optional TTL override and metadata dict.

Invalidate one or all cache entries. Pass cache_key to remove one entry, or flush_all=true to wipe everything.

Analyze a list of chat messages ({role, content}) for token usage and issues. Detects bloated system prompts, near-full context windows, and repeated content. Returns per-role breakdown, issues list, and recommendations.

Token savings dashboard for the current session. Shows cache hits, tokens saved, and estimated USD savings per client.

Remove duplicate messages from a conversation (keeps last occurrence). Returns deduplicated list + tokens saved.