FicelleBlog
Routing, cost, and reliability, in the open.
How Ficelle keeps agents on the best free model without ever spending a cent.
Provider breakage is the silent killer of AI agents
Free and free-tier LLM providers rate-limit, retire models, and misreport capabilities, weekly. If your agent points at one provider, it breaks when they do. Routing with cooldowns, quarantine, and fallback is the fix.
Strict-zero routing: why your agent should never spend behind your back
Most "free LLM" setups have a silent paid fallback. Strict-zero removes that risk: free pricing required, tools required, and no paid fallback, full stop. Here is what that means and why it matters.
Free vs paid LLMs: a 76-task benchmark
We ran 76 real agent tasks through free routing and through GPT-5. On classification, JSON extraction, and reasoning, free was at quality parity. Here is where paying still wins, and how much you save when it does not.