LLM API FAQ

Each model has its own pricing, listed per million tokens on our models page. In some cases, pricing may differ between prompt tokens and completion tokens, or be based on per-request charges depending on the model provider. When you send a request, we calculate the total tokens used and apply the model's base rate, plus a flat 5% fee. This small margin helps us maintain high availability, routing intelligence, and analytics, without any hidden charges. You can view your full usage history, including token counts and costs, directly in your dashboard. We keep billing simple: no markups on model prices beyond our 5% platform fee, and no surprises.