costing-a-model-vs-an-apilisted

Decide whether running your own model actually costs less than paying a hosted API, and at what volume the two cross over. Gathers the real inputs, token counts per request, today's provider pricing, hosting or hardware cost, and one-off training cost, then computes the breakeven point and reports it with the assumptions visible, so the number can be challenged. Use when someone asks whether self-hosting is cheaper, what a fine-tune would save, when owning a model pays for itself, or wants to justify or reject a move off a hosted API. Not for deciding whether the model is good enough, which is evaluating-a-tuned-model, and not for choosing a deployment target.
ErtasAI/open-model-skills · ★ 2 · AI & Automation · score 76

Install: claude install-skill ErtasAI/open-model-skills

# Costing a model vs an API This skill exists to be trustworthy, not persuasive. It answers one question honestly: at this project's actual usage, does owning the model cost less than paying an API per API call, and if not yet, at what volume would it. The honest answer is often "no, stay on the API." Most projects never reach the volume where owning pays for itself, and there is no shame in that. A crossover calculation that only ever concludes in favour of owning is not measuring anything, it is decorating a decision that was already made. ## Gather the real inputs before computing anything Six numbers drive the whole result. Guessing any of them produces a confident-looking number that means nothing: 1. **Tokens in and out per request**, from this project's actual traffic. 2. **Current API pricing** for the model actually being compared against, per million input and output tokens. 3. **Monthly hosting cost**, if the owned model runs on rented infrastructure. 4. **One off training cost**, if a fine-tune is part of the plan. 5. **The amortisation window**, how many months that training cost should be spread across. 6. **Expected or actual monthly request volume**, to know where this project actually sits relative to the breakeven point. Where any of these is not yet known, measure it before computing anything. `references/cost-inputs.md` covers how to get each one honestly: pulling token counts from real request logs instead of guessing, finding a provider's o