Gemini again started producing empty responses

[GV_Zap]

It was working fine until 2 hours ago. Again the same issue empty responses like last week, it started happening again.

[vjaykrsna]

this is so frustrating interrupting the whole workflow. I hope google fixes it soon. It’s been around for a long time the frequency vary.

[BACK_HO_KIM]

i have Same problem again again empty reponses

[Lalit_Kumar]

Hello,

Welcome to the Forum.

Could you please let us know if you are experiencing this issue across all models or only with specific ones?

Additionally, sharing details about the tools you are using and your configuration would help us analyze the issue more effectively.

[GV_Zap]

I am having issues with 2.5 pro model, I just use latest google genai library. This empty response issue started happening for the past 2 weeks, before I didn’t have this issue a single time. It is not 500 internal error, just empty response. Yesterday around 12pm the issue started, and till night 8 pm, the issue didn’t get fixed, then I tried around 3 am, for 70 api calls it worked no issues. Now again the issue seems to be starting.

[Lalit_Kumar]

Hello,

Thank you for sharing the information, we have escalated your issue to concerned team.
Thank you for your patience.

[GV_Zap]

Looks like Gemini API starts failing around Indian time 12 pm, and then it gets fixed late in the night. This is the trend right now for the past few days.

[Krishna_singh1]

I am getting poor code output from Gemini 2.5 Pro and it is not even adhering to the instructions which we are passing in prompts and not giving code in the right structure, sometimes parsing of code also fails. Has anyone faced similar issue?

[GV_Zap]

Yes, don’t use it unless they fix it, otherwise it worsens the situation.

[Krishna_singh1]

I agree. Now another problem is that we can’t even test our system prompts to get same output from other LLMs. we would need to fine tune our system prompts to get a quality output from other models.

[Krishna_singh1]

Thanks Lalit. please ask your team to check the response quality as well. we have a solution which can generate mobile and web apps entirely and now it is giving us lot of code parsing error and quality issues. It started last week. We are completely stuck now.

[cubdesign]

I’ve been using the Gemini 2.5 Pro API as a paid user from Japan, but for about a week now I’ve been frequently experiencing 500 errors and empty responses. I’m uploading PDFs via the File API and then using them in prompts to generate Markdown or JSON output.

[Quantivosolutions]

Same problem. Still getting empty responses and 500 errors

[M_K]

I just found this post and a few others. It looks like I am having the same issue with 2.5 Pro, good to know it’s not just me, bad to know it’s an issue Gemini I have posted here , looks like the same issue Gemini 2.5 Pro - Empty Response-Status 200

There are also these related links:

Empty Response from AI running my clients

I’ve recently started a AI automation business & I have a few clients which I’ve been working with, I built out workflows for them using the Gemini 2.5 Pro & Flash, its been going great for the last month or so & now I have to tell my clients the tools I’ve built for them are on hold & cant be used because of “empty response” from the 2.5 Pro in Make com, That “Modified by moderator” & finding out that this isn’t a one time issue but a recurring one is a big problem when running a business with …

Empty response.text from Gemini 2.5 Pro, despite no safety and max_tokens issues

I got successful responses a couple of times before with the same prompt. However, it’s now returning empty responses, and these are the finish_reason and safety_ratings from the usage_metadata: Finish Reason: STOP. Safety Ratings: N/A Therefore, it doesn’t seem to be a problem with max tokens, nor safety reasons. I already implemented retry with exponential backoff, rotating among different prefixes in my prompt according to a solution suggested here, but nothing is working. Would apprecia…

Gemini 2.5 Pro with empty response.text

Running Gemini 2.5 Pro with grounded search sometimes returns empty response.text with finish_reason of STOP and no other reason. When I inspect the response dict it shows evidence of the search with some web meta information, but nothing else. Any ideas on what is going on? Here is my code: def get_response(seed, model, system_prompt, user_prompt): api_key = os.environ.get('GEMINI_API_KEY') google_search_tool = Tool( google_search=GoogleSearch() ) response = None …

(this thread)

Gemini again started producing empty responses

It was working fine until 2 hours ago. Again the same issue empty responses like last week, it started happening again.

[fengyu]

it took them 2 month to amit there is a problem, so frasturting experinece.