All you need to know about GPT-3, Codex and Embeddings
By Juston and 10 others11 authors92 articles
ChatGPT API Transition Guide
How can I use the ChatGPT API?
Embeddings - Frequently Asked Questions
Guidance on improving latencies
Whisper API FAQ
How can I access GPT-4?
How much does GPT-4 cost?
What is the difference between the GPT-4 models?
Can I fine-tune on GPT-4?
What are the GPT-4 rate limits?
What is the difference between prompt tokens and sampled tokens?
How can I use GPT-4 with images?
How can I use GPT-4 in ChatGPT?
How do I start exploring the API?
How do text-davinci-002 and text-davinci-003 differ?
How do I format my fine-tuning data?
What are tokens and how to count them?
Where do I find my Secret API Key?
Can I fine-tune on text-davinci-003?
How do davinci and text-davinci-003 differ?
How do I create a good prompt?
Doing Math in the Playground
Using logit bias to define token probability
Best practices for prompt engineering with OpenAI API
How do I use Stop Sequences?
How to Use OpenAI API for Q&A and Chatbot Apps
Controlling the length of Completions
Injecting Start and Restart Text in the Playground
Fine-tuning a Classifier to Improve Truthfulness
Why can't I reset my password?
Why am I not receiving my phone verification code?
How can I change my default organization?
Can I change my email address?
How do I switch my authentication method?
How do I change my account password?
How do I invite teammates to my account?
How can I contact support?
Preventing unauthorized usage
Why am I getting an error message stating that I've reached my usage limit?
Rate Limit Advice
Is API usage subject to any rate limits?
How can I solve 429: 'Too Many Requests' errors?
What is the "model is still being loaded" error?
Why am I getting different completions on Playground vs. the API?
Do the OpenAI API models have knowledge of current events?
Why are Playground outputs misclassified as unsafe?
What happened to ‘engines’?
How do I get more tokens or increase my monthly usage limits?
When can I expect to receive my OpenAI API invoice?
Are Playground tokens counted towards my token usage?
How do I check my token usage?
Are the Moderation endpoint and content filter free to use?
What happens after I use my free tokens or the 3-months is up in the free trial?
Is there an SLA for latency guarantees on the various engines?
What's changed with engine names and best practices?
What types of research, academic or otherwise, does OpenAI have a preference for?
Will OpenAI claim copyright over what outputs I generate with the API?
Why did OpenAI choose to release an API instead of open-sourcing the models?
How your data is used to improve model performance
What are OpenAI's policies regarding sharing and publication of generated content?
What specifically will OpenAI do about misuse of the API, given what you’ve previously said about GPT-2?
Which countries and territories are supported by OpenAI?
Adding your API client to the Community Libraries page
API Error Code Guidance
Error Code 401 - Invalid Authentication
Error Code 401 - Incorrect API key provided
Error Code 404 - You must be a member of an organization to use the API
Error Code 429 - Rate limit reached for requests
Error Code 429 - You exceeded your current quota, please check your plan and billing details.
Error Code 429 - The engine is currently overloaded. Please try again later.