GPT-4o Mini: When to Use It Instead of GPT-4o and Save 93% on Costs

from openai import OpenAI

client = OpenAI()

# Perfect use case for mini: simple classification
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "system",
            "content": "Classify the sentiment as: positive, negative, or neutral. Reply with one word."
        },
        {
            "role": "user",
            "content": "The shipping took longer than expected but the product quality exceeded my expectations."
        }
    ],
    max_tokens=10,
    temperature=0
)
print(response.choices[0].message.content)  # "positive" or "neutral"

def route_request(prompt: str, complexity_threshold: int = 500) -> str:
    # Simple heuristic: longer prompts or complex keywords → GPT-4o
    keywords = ["implement", "debug", "analyze", "prove", "architect"]
    is_complex = (
        len(prompt) > complexity_threshold or
        any(kw in prompt.lower() for kw in keywords)
    )
    return "gpt-4o" if is_complex else "gpt-4o-mini"

model = route_request(user_prompt)
response = client.chat.completions.create(
    model=model,
    messages=[{"role": "user", "content": user_prompt}]
)

def estimate_monthly_cost(
    requests_per_day: int,
    avg_input_tokens: int,
    avg_output_tokens: int,
    model: str = "gpt-4o-mini"
) -> float:
    prices = {
        "gpt-4o": (2.50, 10.00),
        "gpt-4o-mini": (0.15, 0.60),
    }
    input_price, output_price = prices[model]
    monthly_input = requests_per_day * 30 * avg_input_tokens / 1_000_000
    monthly_output = requests_per_day * 30 * avg_output_tokens / 1_000_000
    return monthly_input * input_price + monthly_output * output_price

# 100k requests/day, 500 input tokens, 200 output tokens
print(estimate_monthly_cost(100_000, 500, 200, "gpt-4o"))       # $4,200/mo
print(estimate_monthly_cost(100_000, 500, 200, "gpt-4o-mini"))  # $261/mo