I wonder if GPTs can be used with the OpenAI API?
You would have to have GPT Plus to use it.
Will ChatBot AI be able to do this?
#GPTs
hallow warren
tawny kettleBOT
Hi @hallow warren. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
GPTs, or custom versions of ChatGPT, are not directly accessible via the OpenAI API. They are designed to be used within the ChatGPT interface and are included in the ChatGPT Plus and Enterprise plans. GPTs can be customized for specific tasks or topics and can be shared within the ChatGPT platform. However, they cannot be called from other platforms or through the API (source (https://community.openai.com/t/564767)).
If you're a Plus subscriber, you can discover and use versions of ChatGPT (called GPTs) that are customized by the community. These GPTs may combine instructions, extra knowledge, and skills/tools (source (https://help.openai.com/en/articles/8798889-how-can-i-use-gpts)).
On the other hand, the OpenAI API provides more flexibility but requires that you write code or send the requests to the models programmatically. It can be applied to virtually any task and offers a range of models with different capabilities and price points, as well as the ability to fine-tune custom models (source (https://platform.openai.com/docs/introduction)).
In terms of ChatGPT Plus, it offers access to GPT-4 on chat.openai.com with a usage cap, but this does not provide subscribers with access to the API (source (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4)).
So, while you can use GPTs within the ChatGPT interface if you're a Plus subscriber, you cannot use them directly with the OpenAI API. The API and ChatGPT are separate services, each with their own capabilities and use cases.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
hallow warren
@tawny kettle What is the difference between GPTs and the ASSISTANTS API? The assistants API may be similar to GPTs?
tawny kettleBOT
Let me check the knowledge base for you. One moment! :books:
Yes, GPTs and the Assistants API are similar in that they both leverage OpenAI's language models to perform tasks. However, there are several key differences between them:
-
Creation Process: GPTs do not require coding, while the Assistants API requires coding for integration (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
Operational Environment: GPTs are located within ChatGPT, while Assistants can be integrated into any product or service (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
Pricing: GPTs are included in ChatGPT on Plus/Enterprise plans, while Assistants are billed based on usage of different Assistant features (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
User Interface: GPTs have a built-in UI with ChatGPT, while Assistants are designed for programmatic use and can use the playground for visualization (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
Shareability: GPTs have a built-in ability to share with others, while Assistants do not have built-in shareability (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
Hosting: GPTs are hosted by OpenAI, while OpenAI does not host Assistants (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).
-
Tools: Both GPTs and Assistants have built-in tools, but the specific tools vary. For example, GPTs have tools like Browsing, DALL·E, Code Interpreter, Retrieval, and Custom Actions, while Assistants have tools like Code Interpreter, Retrieval, and Function calling (source (https://help.openai.com/en/articles/8673914-gpts-vs-assistants#h_7569ffca53)).