mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #136] API Request failed with invalid json response body #114
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#114
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @undownding on GitHub (Jan 29, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/136
looks like https://github.com/deepseek-ai/DeepSeek-V3/issues/407
most time return an error
some time works correct
@robertalers commented on GitHub (Jan 29, 2025):
Same here!
invalid json response body at https://api.deepseek.com/v1/chat/completions reason: Unexpected end of JSON input
@Tekholms-LW commented on GitHub (Jan 29, 2025):
Same here and most of the time things just timeout. Sometimes the chat model works but I mostly get the same issue invalid json response body" for both
@saintserge commented on GitHub (Jan 29, 2025):
All free/cheap models are have problems from time to time. Google gemini now:
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-thinking-exp-01-21:streamGenerateContent?alt=sse: [429 Too Many Requests]
@yarusl42 commented on GitHub (Jan 30, 2025):
getting the same error
@hanifsajid commented on GitHub (Jan 30, 2025):
It is not supported by the
deepseek-reasonermodel so far.@jhonathas commented on GitHub (Feb 1, 2025):
The same thing happens here. I'm having to set a waiting time before each use to mitigate the problem a little.
@martasvana commented on GitHub (Feb 2, 2025):
Anyone found a solution? Or is it just a problem on DeepSeek's side, that we have no chance to fix ourselves?
Thanks!
@erdemyunsel commented on GitHub (Feb 3, 2025):
same error.
"invalid json response body at https://api.deepseek.com/chat/completions reason: Unexpected end of JSON input"
@Guiguerreiro39 commented on GitHub (Feb 4, 2025):
How am I not seeing more people complaining about this? I'm getting this error pretty much every day. I'm using openai package in nodejs
@Chasen-Zhang commented on GitHub (Feb 5, 2025):
getting the same error
@martasvana commented on GitHub (Feb 5, 2025):
Yes, exactly. I've switched to an OpenAI model in the API for now, and will
wait a couple weeks maybe till the boom around DeepSeek cools down a bit
and they upgrade their servers and implement some basic security features,
haha. And then switch back to DeepSeek in my API.
On Tue, Feb 4, 2025, 03:03 Guilherme Guerreiro @.***>
wrote:
@AndiBird commented on GitHub (Feb 11, 2025):
invalid json response body at https://api.deepseek.com/v1/chat/completions reason: Unexpected end of JSON input
😓
@Ritavdas commented on GitHub (Feb 12, 2025):
Facing the same issues, I am pushing 6-10 API requests at once, most of them fail, only works when I send one at a time.
Even the deepseek-coder one is giving the same problem
@tolerious commented on GitHub (Feb 14, 2025):
Facing the same issue. 😢
@Joonas12334 commented on GitHub (Feb 16, 2025):
So it seems like a their issue? I have a 80% chance of getting it while using the api. Sometimes it works fine tho.
@AndiBird commented on GitHub (Feb 16, 2025):
Yes, @Joonas12334 , sometimes it works, but it's awful because you never know when it's going to fail. That's why, even though ChatGPT's API is expensive, it offers much more reliability.
@Joonas12334 commented on GitHub (Feb 16, 2025):
I just switched to google gemini. It's also fantastic if guided well. Also damn. It's really fast compared to deepseek. Howerver still eager to try out deepseek more when it becomes actually usable (if that ever happens)
@AndiBird commented on GitHub (Feb 16, 2025):
X2, bro
@kimkong88 commented on GitHub (Feb 20, 2025):
their service status suggests that api performance has been degraded.... will this ever get better?
@ltomov commented on GitHub (Feb 25, 2025):
They probably can't handle the load at that super low price.
It would be useful to at least output some better error, like "Server is temporary down", to prevent people from spending time, wondering if they can do something to fix it.
@github-actions[bot] commented on GitHub (Apr 8, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@github-actions[bot] commented on GitHub (May 9, 2025):
false