I was wondering if I don't enable auto-recharge how long I can use the API?
#question
brittle charm
molten sigilBOT
Hi @brittle charm. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
You can use the OpenAI API as long as you have credits in your account. Once you've consumed all your credits, your API requests will start returning an error letting you know you've hit your billing quota. If you'd like to continue your API usage, you can return to the billing portal and use the "Add to balance" button to purchase additional credits.
Please note that any purchased credits will expire after 1 year and they are non-refundable. If you don't enable auto-recharge, you'll need to manually add credits to your account when your balance is low or depleted.
You can check your usage and credit balance on your account page on the OpenAI platform. If you have any issues or further questions, you can contact OpenAI support.
Sources:
- Help Article > En > Articles Part 2 (https://help.openai.com/en/articles/8264644-what-is-prepaid-billing)
- Forum Post: Understanding API limits and free tier > Official Answer (https://community.openai.com/t/498517)
- Forum Post: Openai api paiment method > Official Answer (https://community.openai.com/t/630596)
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
brittle charm
@molten sigilI was also wondering if the API wasn't too expensive last time it cost €30
molten sigilBOT
Let me check the knowledge base for you. One moment! :books:
The cost of using the OpenAI API depends on the specific model you're using and the amount of data you're processing. For example, the GPT-4 model has different pricing for models with different context lengths:
- For models with 128k context lengths (e.g.
gpt-4-turbo), the price is $10.00 / 1 million prompt tokens (or $0.01 / 1K prompt tokens) and $30.00 / 1 million sampled tokens (or $0.03 / 1K sampled tokens). - For models with 8k context lengths (e.g.
gpt-4andgpt-4-0314), the price is $30.00 / 1 million prompt tokens (or $0.03 / 1K prompt tokens) and $60.00 / 1 million sampled tokens (or $0.06 / 1K sampled tokens). - For models with 32k context lengths (e.g.
gpt-4-32kandgpt-4-32k-0314), the price is $60.00 / 1 million prompt tokens (or $0.06 / 1K prompt tokens) and $120.00 / 1 million sampled tokens (or $0.12 / 1K sampled tokens).
Please note that these prices are in USD. The exact cost in Euros will depend on the current exchange rate. You can find the most up-to-date pricing information on the OpenAI Pricing page (https://openai.com/pricing).