GPT 4o costs $0.15/min?
# support
e
Why is the dashboard showing GPT 4o as costing $0.15/min and GPT 4 Turbo costing $0.31/min?
v
Hi @Edpreble, I'm an AI assistant for Vapi. I'll analyze available sources and get back to you shortly.
----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Estimating Costs]() * [Billing Examples]() * [Pricing Overview]() * [Connecting Your Custom LLM to Vapi: A Comprehensive Guide]() -----------------------------
### Answer The costs you're seeing on the dashboard for GPT-4o at $0.15/min and GPT-4 Turbo at $0.31/min reflect the different rates charged by the providers for these models. Each model may have different computational needs and associated costs, which can result in varying charges per minute. For detailed and specific pricing information, you can check directly with the provider's pricing pages or refer to Vapi's documentation for provider-specific costs [(1)]() .
Got it. Tagging @User for additional help.
s
Because both of them are different model with different pricing.
e
I get they are priced differently, but $0.15/min and $0.31/min is exorbitant. GPT 4o and GPT 4 should be less than a penny per min. Am I missing something?
s
Okay, so basically the thing that you see isn't the exact amount, but rather an approximation. It can be either low or high depending upon the input and output that was generated. What you can do is simply make a call and after this, just calculate the cost on the basis of that call input and output token. You can find the exact cost at https://openai.com/api/pricing/. If you find any discrepancy, let me know.
2 Views