bolt.diy: There was an error processing your request: An error occurred.

Describe the bug

Hi there, I have place my API key from OpenAI in my .env and on the local website but same error everytime so i cant use this chat

Link to the Bolt URL that caused the error

http://localhost:5173/

Steps to reproduce

  1. Starting project in cmd with pnpm run dev
  2. Go in http://localhost:5173/
  3. Select OpenAI with GPT-4o
  4. Writting prompt
  5. Error occurred

Expected behavior

Let it work

Screen Recording / Screenshot

image

Platform

  • OS: Windows
  • Browser: Chrome Canary
  • Version: Version 133.0.6907.0 (Build officiel) canary (64 bits)

Provider Used

OpenAI

Model Used

GPT-4o

Additional context

No response

About this issue

  • Original URL
  • State: closed
  • Created 2 years ago
  • Reactions: 3
  • Comments: 47

Commits related to this issue

Most upvoted comments

After many tests and trying all the tips I found on the internet, only one solution worked.

Although it seems like a local problem, or in the platform, it is actually an API problem, or rather, it seems to me that somehow the APIs are not recognizing or validating the requests from the local Bolt, and I can’t imagine why this is happening.

The only solution that worked for me was to disable all providers and base urls, except Mistral. I created an API to use with Mistral Large Las, and bingo! Everything worked perfectly.

image

I hope it works for you!