import instructor
from time import sleep
from pydantic import BaseModel, field_validator
from openai import OpenAI
class FakeClass(BaseModel):
    insight: str
client = instructor.from_openai(OpenAI(api_key=OPENAI_API_KEY))
fake_str = "This is a Test string" * 1000

for x in range(0, 3):
    sleep(1)
    insight, completion = client.chat.completions.create_with_completion(
        model="gpt-4o",
        messages=[
            {
                "role": "system",
                "content": fake_str,
            },
            {"role": "user", "content": "Test User Prompt"},
        ],
        max_retries=1,
        response_model=FakeClass,
    )
 
    print(completion.usage.prompt_token_details.model_dump())

{'audio_tokens': 0, 'cached_tokens': 0}

open_ai_client = OpenAI(api_key=OPENAI_API_KEY)
open_ai_client.chat.completions.create

for x in range(0, 3):
    sleep(1)
    chat_completion = open_ai_client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "system",
                "content": fake_str,
            },
            {"role": "user", "content": "Test User Prompt"},
        ],
    )

    cached_tokens = chat_completion.usage.prompt_tokens_details.cached_tokens
    if cached_tokens == 0:
        print("No cached tokens")
    else:
        print(f"Tokens used: {cached_tokens}")
        print(chat_completion.usage.prompt_tokens_details.model_dump())