What it does
An OpenAI-compatible gateway and SDK for calling many model providers with budgets, logging, load balancing, guardrails, and cost tracking.
Why it belongs here
The most direct tokenmaxxing fit: route calls, track spend, enforce budgets, and stop pretending every prompt deserves the priciest model.
Best use case
Teams that want one gateway for provider abstraction, model routing, usage logging, budgets, fallbacks, and cost-aware defaults.
How to use it
Put it between the app and model providers, tag requests by workflow, set spend limits, and route low-risk tasks to cheaper models after evals pass.
Limits
A gateway will not fix vague prompts or poor review loops by itself. Budget rules need ownership and ongoing tuning.
Tags
gatewaycost-trackingrouting
