cai/examples/support_bot/data/article_6901266.json

{"text": "The latency of a completion request is mostly influenced by two factors: the model and the number of tokens generated. Please read our updated documentation for [guidance on improving latencies.](https://beta.openai.com/docs/guides/production-best-practices/improving-latencies) \n\n", "title": "Guidance on improving latencies", "article_id": "6901266", "url": "https://help.openai.com/en/articles/6901266-guidance-on-improving-latencies"}