Calculating the cost
Before deploying AI features at scale, it's essential to estimate costs. The cost is dependent on the number of input and output tokens used and the model chosen.
Your task is to calculate the cost of summarizing customer chat transcripts.
The OpenAI client, along with text, prompt, and max_completion_tokens, are preloaded for you.
Deze oefening maakt deel uit van de cursus
Working with the OpenAI API
Oefeninstructies
- Extract the input token usage from the
response. - Complete the cost calculation to add the output token cost.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
client = OpenAI(api_key="")
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": prompt}],
max_completion_tokens=max_completion_tokens
)
input_token_price = 0.15 / 1_000_000
output_token_price = 0.6 / 1_000_000
# Extract token usage
input_tokens = response.____.____
output_tokens = max_completion_tokens
# Calculate cost
cost = (input_tokens * input_token_price + ____ * ____)
print(f"Estimated cost: ${cost}")