[BUG] Constant API Error and request timeouts
Environment
- Platform (select one):
- [ ] Anthropic API
- [ ] AWS Bedrock
- [ ] Google Vertex AI
- [x] Other: Claude code
- Claude CLI version: 1.0.21
- Operating System: Ubuntu 24.04
- Terminal: Gnome Terminal
Bug Description
This is what I keep getting today after one prompt:
⎿ API Error (Request timed out.) · Retrying in 1 seconds… (attempt 1/10)
⎿ API Error (Request timed out.) · Retrying in 1 seconds… (attempt 2/10)
⎿ API Error (Request timed out.) · Retrying in 2 seconds… (attempt 3/10)
⎿ API Error (Request timed out.) · Retrying in 4 seconds… (attempt 4/10)
⎿ API Error (Request timed out.) · Retrying in 9 seconds… (attempt 5/10)
⎿ API Error (Request timed out.) · Retrying in 20 seconds… (attempt 6/10)
⎿ API Error (Request timed out.) · Retrying in 37 seconds… (attempt 7/10)
⎿ API Error (Request timed out.) · Retrying in 36 seconds… (attempt 8/10)
⎿ API Error (Request timed out.) · Retrying in 37 seconds… (attempt 9/10)
⎿ API Error (Request timed out.) · Retrying in 37 seconds… (attempt 10/10)
⎿ API Error: Request timed out.
After this it stays offline permanently.
Steps to Reproduce
- Start Claude Code
- Write a 10-15 lines prompt
- Wait forever.
Expected Behavior
I expect it to work.
Actual Behavior
It's timed out and now it's permanently offline
Additional Context
Should I continue paying for this, upgrade to a more expensive plan or switch to something that actually works?
I got better results running local stuff with Ollama for free.
12 Comments
I think is the same problem that is making Claude Code unusable for days now.
!Image
Im cancelling my subscription and getting a key on openrouter. ffs
How to cancel my subscription? I want to do it too.
the problem is "env": { "MAX_THINKING_TOKENS": "32000" } , remove it
Where can we find the "env": { "MAX_THINKING_TOKENS": "32000" }? Thanks.
.claude>settings.local.json if you have "env": { "MAX_THINKING_TOKENS": "32000" } delete it
I do not config the settings.local.json. I change the workplace to an empty one. Then start claude. The problem still exists.
cwd: /home
⎿ API Error (Request timed out.) · Retrying in 1 seconds… (attempt 1/10)
⎿ API Error (Request timed out.) · Retrying in 1 seconds… (attempt 2/10)
⎿ API Error (Request timed out.) · Retrying in 2 seconds… (attempt 3/10)
⎿ API Error (Request timed out.) · Retrying in 4 seconds… (attempt 4/10)
⎿ API Error (Request timed out.) · Retrying in 10 seconds… (attempt 5/10)
⎿ API Error (Request timed out.) · Retrying in 20 seconds… (attempt 6/10)
⎿ API Error (Request timed out.) · Retrying in 33 seconds… (attempt 7/10)
⎿ API Error (Request timed out.) · Retrying in 36 seconds… (attempt 8/10)
⎿ API Error (Request timed out.) · Retrying in 37 seconds… (attempt 9/10)
⎿ API Error (Request timed out.) · Retrying in 39 seconds… (attempt 10/10)
⎿ API Error: Request timed out.
Maybe you should create an empty settings.local.json inside .claude folder, or try /logout
The above methods do not work either.
Sorry to hear that I don't know any other options
From Anthropic Support to me:
"The timeout issues with long todo lists appear to be related to the extended processing time required for complex multi-step tasks, which can exceed the default API timeout limits. As a workaround, you can increase the API timeout by setting the API_TIMEOUT_MS environment variable before launching Claude Code. For example, you can use the export API_TIMEOUT_MS=600000 command to set it for 10 minutes. The default appears to be 30 seconds (30000ms), but you can increase it significantly for complex tasks like long todo lists."
This worked for me personally.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.