OpenAI

Please visit our <a href="https://platform.openai.com/docs/api-reference/chat/create" rel="nofollow noopener noreferrer" target="_blank">Create chat completion</a> API documentation for details for how to call this model. To see how many tokens are in a text string without making an API call, you can use OpenAI’s <a href="https://github.com/openai/tiktoken" rel="nofollow noopener noreferrer" target="_blank">tiktoken</a> Python library. Example code can be found in the OpenAI Cookbook’s guide on <a href="https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb" rel="nofollow noopener noreferrer" target="_blank">how to count tokens with tiktoken</a>.

Is fine-tuning available for the <code>gpt-3.5-turbo</code>?

Currently, we only support fine-tuning of our base models. Please review the <a href="https://platform.openai.com/docs/guides/fine-tuning" rel="nofollow noopener noreferrer" target="_blank">fine-tuning guide</a> for more details.

Does OpenAI store the data that is passed into the API?

As of March 1st, 2023, we retain customer API data for 30 days but no longer use customer data sent via the API to improve our models. You can learn more in our <a href="https://platform.openai.com/docs/data-usage-policy" rel="nofollow noopener noreferrer" target="_blank">data usage policy</a>.

How do I keep the Chat session focused on a topic?

The main way to keep the conversation focused on a topic is the system message. You can set this

What's the rate limits for the ChatGPT API?

Free trial users: 20 RPM 40000 TPM Pay-as-you-go users (first 48 hours): 60 RPM 60,000 TPM Pay-as-you-go users (after 48 hours): 3500 RPM 90,000 TPM