Source: https://www.rightmodeler.com/blog

# The rightmodeler blog

Notes on measuring model decisions: what the evidence supports, what it does not, and what we changed our minds about.

- [LLM cost optimization tools: which approach fits your workload?](https://www.rightmodeler.com/blog/llm-cost-optimization-tools): Substitution, routing, caching, compression, batching and fine-tuning each fix a different LLM cost problem. How to match one to your workload and prove it.
- [How an AI gateway can invalidate your model evaluation.](https://www.rightmodeler.com/blog/llm-gateway-evaluation-pitfalls): A fallback, an alias, a cached answer or a rewritten request can make an evaluation grade something other than the candidate. Each can be caught and fixed.
- [Langfuse vs Helicone: tracing, evaluation, gateways, and cost analysis.](https://www.rightmodeler.com/blog/langfuse-vs-helicone): Langfuse instruments your code; Helicone sits in the request path. How they compare on tracing, evals, prompts, gateways, caching, cost, and self-hosting.
- [Bifrost vs LiteLLM: a practical evaluation checklist.](https://www.rightmodeler.com/blog/bifrost-vs-litellm): Choosing between Bifrost and LiteLLM? A hands-on checklist for setup and keys, model catalogs, log exports, routing controls, and replaying a cheaper model.
- [Nobody can predict the bill.](https://www.rightmodeler.com/blog/nobody-can-predict-the-bill): Eight frontier models, 500 real GitHub issues, four runs each. A new paper finds nobody can predict what an agent task costs, including the agent.
- [The bill nobody can read.](https://www.rightmodeler.com/blog/the-bill-nobody-can-read): Why your agent bill has no line items, and what to do about it. Part one of the rightmodeler vision: Crucible for AI agent analytics and optimization.
- [The Tuesday problem.](https://www.rightmodeler.com/blog/the-tuesday-problem): Why evaluating every new model becomes a project nobody budgets. Part two of the rightmodeler vision: turning model migrations into pull requests.
- [We were picking models by vibes. Then the bill arrived.](https://www.rightmodeler.com/blog/why-we-built-rightmodeler): We picked models by instinct for years, then defaulted to the frontier model and paid for it. rightmodeler measures candidates against outputs you accepted.