Blog

A leaderboard can't choose your model for you. The method that actually works: define the job, test two or three candidates on your own traffic, score cost per finished answer, latency and quality, then decide whether to pin or route.

Switch from api.anthropic.com to FluxRouter in three lines: new base URL, new key, new model id. Same Anthropic SDK, same Claude Code. Plus the spend-tracking gotcha most people miss.

Keep your OpenAI SDK, your endpoints, your request JSON. Change the base URL, the key, and the model string, and you pick up per-request dollar cost on the response, streaming included once you set include_usage. Full cutover checklist included.

One week, three platforms, two massive repos refactored in parallel by a fleet of agents that prove every claim before it lands. This is the exact operating system behind it: every rule, every gate, every receipt.

Get schema-valid JSON out of Flux with one field. json_object vs json_schema, runnable Python and curl, why support rides on the served model, how to pin one, how to read which model answered, and the one validation line you still owe yourself.

Asking a model nicely for JSON is a probabilistic hope. A schema-enforced output mode moves the guarantee from the prompt into the decoder. Here is why the difference shows up as quiet, expensive failures your try/except never catches, the honest limits across models, and the decision order to ship it.

What an LLM gateway actually is, how it differs from a router and a raw provider SDK, when you genuinely don't need one, and how to trust any gateway by what it shows you about one live request.

Per-token price is a decoy. The number that runs your AI bill is dollars per completed answer. Here's how to measure it, control it, and govern it, with a real cost receipt on every request.

A router company on when to build your own LLM gateway instead of buying one. The real test: is routing your product or your plumbing? Plus a copy-paste decision checklist.

A spreadsheet only works while someone is watching it. Here's the lightweight operating model that governs AI spend on its own: a standing ceiling, a cost receipt on every request, and one invoice.