GPT-4 is already arranged!

Right in 3 A day ago， OpenAI released smarter, more powerful (and more expensive) GPT-4 models，Drop Ge Smart Chat applied for API permissions at the first time。After receiving the mail this morning，Drop Ge Smart Chat supported the model for the first time。

Now，You can use the GPT-4 model on Drop Chat，The default is the latest model。--of course，Considering that the GPT-4 model is more expensive，And relatively slowly，We provide an option for model selection，If necessary，You can also switch models for a lower price，Faster GPT-3.5-turbo. This setting now supports cloud synchronization，Set it once，Telegram Bot will also take effect。

limit

Since this is the first GPT-4 model，As far as the test results are concerned，It has some more obvious limitations：

The model firmly believes that it is GPT-3.5-turbo and not GPT-4，However, you can tell from the amount of points consumed 3.5 still is 4；
The model is slow，But it's actually acceptable，In the near future, OpenAI will improve speed optimization；
Model API processing capacity is small，Currently, GPT-4 requests are limited to 200 Per minute，Than 3.5 of 3500 Speaking，A lot smaller。If you keep getting errors，Please switch to GPT-3.5 for the time being；
Currently we only have the GPT-4 API，There is no GPT-4-32k API，In the future, we will support it as soon as we get it；
Although the GPT-4 model supports image recognition，But it seems that we haven't been able to find documentation related to images at the moment，Therefore, support is not available at this time。

Pricing

Since GPT-4 makes a distinction between input and output pricing，Here, too, we have differentiated pricing，input，That is, Prompt，Includes all the history of the chat，Will consume 0.3 per 1000 token；output，That is, what the model gives，Will consume 0.6 per 1000 token。

In the future, if OpenAI adjusts the price，We will also make adjustments to the response，Please note。

Another，If you switch to GPT-3.5 ，Then the point consumption will be charged according to the original GPT-3.5 pricing。