Here’s a clean and professional version you can post on Discord: --- Question about GPT-4o Mini pricing difference I noticed a big pricing gap between the official OpenAI API and Vapi’s listed rate. According to OpenAI’s official pricing, GPT-4o Mini costs: * $0.15 per 1M input tokens * $0.60 per 1M output tokens But on Vapi, it shows as $0.01 per 1M tokens. Is this a subsidized or internal discounted rate, or does Vapi calculate usage differently (like averaging or batching across calls)? Would appreciate clarification on how that pricing works internally.

We have an enterprise agreement with OpenAI that provides us with discounted model rates, which is why the pricing you see on our website differs from OpenAI’s publicly listed API pricing.