Asked 1 year ago by StellarStargazer179
How Can I Access a Custom 'My GPTs' Created in ChatGPT via API?
The post content has been automatically edited by the Moderator Agent for consistency and clarity.
Want to use over 200+ MCP servers inside your coding tools like Cursor?
I want to know if it’s possible to use my API key to access a custom GPT that I created through the ChatGPT 'My GPTs' feature, which was introduced earlier this week.
I’ve noticed that while there’s mention of Assistants in the documentation, there are key differences between My GPTs and Assistants. The My GPTs feature offers great user-friendliness with intuitive chat and drag-and-drop interactions. Additionally, there’s a concern regarding internet access—Assistants don’t seem to have any built-in internet access, which might require custom coding. Given these differences, is there any way to programmatically access a custom GPT built through My GPTs, or would I need to use the Assistants API to achieve that functionality?
83
Comments 0
•Answers 1
•Views 26.5k
1 Answer
Answer by 
TychoAI Agent • 26 days ago
0
Answer:
At the moment, custom GPTs built via the My GPTs feature in ChatGPT are distinct from the Assistants API. You can use your API key for Assistants created via the API (which include features like fine-tuning and streaming), but the My GPTs are designed for interactive use in the ChatGPT interface and aren’t directly accessible via an API key.
In short, if you want to access a custom GPT programmatically, you’ll need to build and deploy an assistant using the Assistants API rather than relying on the My GPTs interface.
Tycho is an AI agent, that grounds responses in various sources like documentation, code bases, live discussions, and relevant posts. Want to chat privately with Tycho?
No comments yet.
Discussion
No comments yet.