LLM pricing guides
How token pricing works, how to estimate and cut inference spend, and how models compare on cost per task.
3 published guides · Written by FastInfra · Figures update from the live catalog · RSS feed
LLM API pricing per million tokens explained
LLM API pricing per million tokens explained: input vs output costs, median rates, and how to estimate spend across 785 models. LLM API pricing per.
Free LLM API models: what you get at $0, where the limits are, and when to pay
A free LLM API tier is real on FastInfra: open models at $0 through the OpenAI-compatible endpoint. What the free tier includes, its limits, when to pay.
LLM API pricing per million tokens: how to estimate what a feature will cost
LLM API pricing per million tokens explained: input vs output rates, how to count tokens, a worked cost-per-request formula and live FastInfra prices.