Is it a limit to the gpt 4 model if you use it in your api? To clearify, when using the gpt 4 model normally, you have a message limit for a specific period of time, does that also apply to the API's if using the gpt 4 model on your API?
#API limit?
stray bridge
exotic domeBOT
Hi @stray bridge. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Yes, there are rate limits when using the GPT-4 model via the API. However, it's important to note that these API rate limits are independent of the message limits for ChatGPT Plus subscribers. The exact details of these API rate limits were not provided in the extracts, but you can learn more about them in the OpenAI documentation (https://help.openai.com/en/articles/5955598-is-api-usage-subject-to-any-rate-limits).
For ChatGPT Plus subscribers, as of January 5th, 2024, GPT-4 has a limit of 40 messages every 3 hours. This limit may be dynamically adjusted depending on demand and system performance. It's also worth noting that subscribing to ChatGPT Plus does not provide access to the API.
Please be aware that GPT-4 is an inference model and does not have access to the internet or any other system. Any such access has to be implemented by the services that drive this model. If you use GPT-4 through the API, you’re responsible for providing those services as appropriate.
Sources:
- How can I access GPT-4? (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4)
- Does GPT-4 API Have Access to the internet? (https://community.openai.com/t/468615)
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
stray bridge
Can you pay to have extend the rate limits?
@exotic dome Can you pay to have extend the rate limits?
exotic domeBOT
Let me check the knowledge base for you. One moment! :books:
Yes, you can increase your rate limits by increasing your usage tier. As your usage of the OpenAI API and your spend on the API goes up, OpenAI automatically graduates you to the next usage tier, which usually results in an increase in rate limits across most models.
Here are the usage tiers and their qualifications:
| Tier | Qualification | Usage limits |
|---|---|---|
| Free | User must be in an allowed geography (https://platform.openai.com/docs/supported-countries) | $100 / month |
| Tier 1 | $5 paid | $100 / month |
| Tier 2 | $50 paid and 7+ days since first successful payment | $500 / month |
| Tier 3 | $100 paid and 7+ days since first successful payment | $1,000 / month |
| Tier 4 | $250 paid and 14+ days since first successful payment | $5,000 / month |
| Tier 5 | $1,000 paid and 30+ days since first successful payment | $10,000 / month |
You can view your current rate limits, your current usage tier, and how to raise your usage tier/limits in the Limits section (https://platform.openai.com/account/limits) of your account settings.
Sources:
- What are the GPT-4 rate limits? (https://help.openai.com/en/articles/7127986-what-are-the-gpt-4-rate-limits)
- Rate Limits and 429: 'Too Many Requests' Errors (https://help.openai.com/en/articles/6843909-rate-limits-and-429-too-many-requests-errors)
- API rate limit advice (https://help.openai.com/en/articles/6891753-api-rate-limit-advice)
- Usage tiers (https://platform.openai.com/docs/guides/rate-limits?context=tier-free)