Stimare il costo di una richiesta prima di chiamare un modello

import math
import os

prompt = "Write a short product description for CometAPI."
max_output_tokens = 200

input_price_per_1m = float(os.environ["MODEL_INPUT_PRICE_PER_1M"])
output_price_per_1m = float(os.environ["MODEL_OUTPUT_PRICE_PER_1M"])

estimated_input_tokens = math.ceil(len(prompt) / 4)

estimated_cost = (
    estimated_input_tokens * input_price_per_1m
    + max_output_tokens * output_price_per_1m
) / 1_000_000

print(f"Estimated maximum cost: ${estimated_cost:.6f}")

Estimated maximum cost: $0.000123

curl https://api.cometapi.com/v1/chat/completions \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "your-model-id",
    "messages": [
      {
        "role": "user",
        "content": "Write a short product description for CometAPI."
      }
    ],
    "max_completion_tokens": 200
  }'

{
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 42,
    "total_tokens": 52
  }
}

const taskCount = 3;
const pricePerTask = Number(process.env.MODEL_PRICE_PER_TASK);

const estimatedCost = taskCount * pricePerTask;

console.log(`Estimated maximum cost: $${estimatedCost.toFixed(4)}`);

Estimated maximum cost: $0.4500