> No system prompt support—the models use the existing chat completion API but you can only send user and assistant messages.
> No streaming support, tool usage, batch calls or image inputs either.
I think it's worth adding a note explaining that many of these limitations are due to the beta status of the API. max_tokens is the only parameter I've seen deprecated in the API docs.
> We will be adding support for some of these parameters in the coming weeks as we move out of beta. Features like multimodality and tool usage will be included in future models of the o1 series.
I wonder if it supports Structured Output / JSON Mode. That would make a big difference to programmatic use. I guess I will try it later when I have time.
> No streaming support, tool usage, batch calls or image inputs either.
I think it's worth adding a note explaining that many of these limitations are due to the beta status of the API. max_tokens is the only parameter I've seen deprecated in the API docs.
From https://platform.openai.com/docs/guides/reasoning
> We will be adding support for some of these parameters in the coming weeks as we move out of beta. Features like multimodality and tool usage will be included in future models of the o1 series.