OpenAI: gpt-3.5-turbo-instruct API

gpt-3.5-turbo-instruct-0914 is a non-chat model developed by OpenAI, specifically optimized for instruction-following tasks. It serves as a drop-in replacement for legacy models like text-davinci-003, maintaining GPT-3 era completion characteristics while offering better efficiency and lower costs. Unlike chat-optimized models, it is designed for the legacy Completions endpoint rather than Chat Completions. It excels at direct single-turn instructions, text editing, code completion, and tasks requiring straightforward logical execution.

Frequently Asked Questions

What is the context window of gpt-3.5-turbo-instruct?

gpt-3.5-turbo-instruct supports a context window of up to 4,095 tokens.

What is the knowledge cutoff of gpt-3.5-turbo-instruct?

The knowledge cutoff of gpt-3.5-turbo-instruct is 2021-08-31.