Where can I buy tokens for GPT-4?
Hello,
I'm currently programming a voice assistant and wanted to connect it to GPT-4. I purchased 50,000 tokens from Shop – ChatGPT , but when I start the program, it says I still don't have access to GPT-4. Do I need to buy the tokens somewhere else?
My code:
import openai import pyttsx3 import re import pyjokes import speech_recognition as sr from pyowm import OWM import spotipy from spotipy.oauth2 import SpotifyOAuth import time import random import datetime import pytz from geopy.geocoders import Nominatim from timezonefinder import TimezoneFinder openai.api_key = 'sk-...' model_id = "gpt-4" engine = pyttsx3.init() def recognize_speech(): recognizer = sr.Recognizer() while True: with sr.Microphone() as source: print("Sage etwas...") audio = recognizer.listen(source, timeout=15) try: text = recognizer.recognize_google(audio, language="de-DE") print("Text: " + text) return text except sr.UnknownValueError: return "not_understood" except sr.RequestError as e: print(f"Fehler bei der Anfrage an die Google Web Speech API: {e}") return "" def openai_request(prompt): response = openai.ChatCompletion.create( model=model_id, messages=prompt ) api_usage = response['usage'] print('Total Token consumed: {0}'.format(api_usage['total_tokens'])) prompt.append({'role': response.choices[0].message.role, 'content': response.choices[0].message.content}) return prompt def speak(text): engine.say(text) engine.runAndWait() def ausführen(): while True: q = recognize_speech() print("Erkannter Text:", q) if q == "not_understood": speak("Entschuldigung! Das habe ich nicht verstanden.") break elif not q: break elif "hallo" in q: speak('Hallo! Womit kann ich dir behilflich sein?') break else: prompt = [{'role': 'user', 'content': q}] prompt = openai_request(prompt) response = prompt[-1]['content'] speak(response) if __name__ == '__main__': ausführen()
Error code:
C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Scripts\python.exe C:\Users\User\PycharmProjects\voiceAssistant\main.py
Say something…
Text: when was the First World War
Recognized text: when was the First World War
Traceback (most recent call last):
File "C:\Users\User\PycharmProjects\voiceAssistant\main.py", line 83, in <module>
carry out()
Run file "C:\Users\User\PycharmProjects\voiceAssistant\main.py", line 77
prompt = openai_request(prompt)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\PycharmProjects\voiceAssistant\main.py", line 43, in openai_request
response = openai.ChatCompletion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^
File "C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Lib\site-packages\openai\api_requestor.py", line 298, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Lib\site-packages\openai\api_requestor.py", line 700, in _interpret_response
self._interpret_response_line(
File "C:\Users\User\PycharmProjects\voiceAssistant\venv\interpreter\Lib\site-packages\openai\api_requestor.py", line 765, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: The model `gpt-4` does not exist or you do not have access to it. Learn more: https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4.
Process finished with exit code 1
Kind regards
There are no tokens from GPT. Your shop you found is a third-party provider that does not officially work with OpenAI. This shop probably reads your data. Do not use unknown third-party providers that are not verified. The official model is offered by OpenAI and is only offered as a subscription. As much as you use, you will be debited from your credit card. That means you have to pay a little. There is no other way. If you want a free option, you can also use Meta LLAMA. This is completely free and runs directly on your PC.
I didn’t buy the tokens with my credit card, so the problem that they have my data, at least I didn’t. However, I have to deposit the credit card somewhere (at the official openAI website) that it automatically withdraws the money but I don’t know where.
Thanks anyway
You can find information about ChatGPT 4 pricing models here: https://openai.com/pricing
Thank you.
In OpenAI, a tab called pricing or something like that might exist.
Thank you for your answer! But there is just how much 1k tokens cost for every model and not how or where to buy it
https://platform.openai.com/account/billing/overview. You need to have $5 to start
It’s an Abo Model. You pay as much as you need, no more, no less. That means you always have to pay a little. However, as prices are quite favourable, it should not be too expensive
No problem
Thank you.