#Rate limits

1 messages · Page 1 of 1 (latest)

merry sphinx
#

What are the rate limits for gpt-3.5-turbo-1106?

charred flickerBOT
#

Hi @merry sphinx. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

The rate limits for the GPT models, including gpt-3.5-turbo-1106, are dependent on your usage tier. The usage tiers are based on how much you have already paid to use the API. Here is a summary of the tiers:

  • Tier 0: 10,000 Tokens Per Minute (TPM)
  • Tier 1 ($5 paid): 20,000 TPM
  • Tier 2 ($50 paid and 7+ days since first successful payment): 40,000 TPM
  • Tier 3 ($100 paid and 7+ days since first successful payment): 80,000 TPM
  • Tier 4 ($250 paid and 14+ days since first successful payment): 300,000 TPM
  • Tier 5 ($1,000 paid and 30+ days since first successful payment): 300,000 TPM

You can find which usage tier you are on your Limits settings page on the OpenAI platform. Please note that these rate limits are subject to change and it's always best to check the official OpenAI documentation for the most up-to-date information.

For more details, you can refer to the official page (https://platform.openai.com/docs/guides/rate-limits/usage-tiers) on OpenAI's platform.

If you hit a rate limit error, it means that API requests are being sent too quickly. You can handle this by spacing out your requests or running fewer parallel processes. If you continue to have issues, you can contact OpenAI support at support@openai.com.

Please note that the rate limits for the gpt-3.5-turbo-1106 model specifically were not mentioned in the extracts provided. The information above applies generally to GPT models and may not be accurate for gpt-3.5-turbo-1106. For the most accurate information, please refer to the official OpenAI documentation or contact OpenAI support.

#

@merry sphinx kapa.ai is still learning and improving, please let us know how it did by reacting below

stiff acorn
#

Hello! i'm getting a rate limit when trying to generate images using the openai sdk in dall-e-3, the error says : 429 Rate limit exceeded Limit: 0/1min. Current: 1/1min
It's weird cuz the limit is actually 0 images per minute so idk if it's a bug or a restriction