OpenAI's o1 and o1 mini models available in V7 Go

We've integrated OpenAI's latest model series, o1 and o1 mini, into V7 Go behind a feature flag. These models are pre-trained for chain-of-thought reasoning, making them ideal for complex tasks in data analysis, coding, and mathematical problem-solving.

These models prioritize accuracy over speed, taking more time to "think" before responding. While o1 outperforms GPT-4o in reasoning, it may not be suitable for all tasks. Please note the current rate limits of 100 requests per minute may cause errors, and they have higher token costs compared to GPT models.