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, n…

Hi @Tatiane_Wu_Li , Welcome to the Forum, To help us understand the empty response.text issue, could you share a code snippet to reproduce the issue? Thank you!

[image] Gemini 2.5 Pro with empty response.text Gemini API 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 …

I don’t think using grounded search is the culprit. The issue increased in the last weeks but today and yesterday it went insane. I use the same prompt every day, with variations, for testing a lot. Other forums also report that today and yesterday were really bad. None of these reports call out usi…

I have also started running into this as of three days ago, even when running low-token prompts just using curl directly. A response from Gemini is hit-or miss, it either responds as expected, gives an error 500, or gives a STOP without any content. Could it be overloaded?

Been using the same 2.5 Pro setup for weeks with no issues, but now I keep getting empty responses with finish_reason: stop . My retry loop fails more often than not, even after adding exponential backoff. Tried using unique identifiers (timestamps, request IDs, session IDs) and the Uniueq fix — nei…

[image] sabrina_khazanov: Been using the same 2.5 Pro setup for weeks with no issues, but now I keep getting empty responses with finish_reason: stop . My retry loop fails more often than not, even after adding exponential backoff. Tried using unique identifiers (timestamps, request IDs, sess …

llm_client file class BaseLLMClient(ABC): """Abstract Base Class defining the interface for all LLM clients.""" def __init__(self, model: str): self.model = model @abstractmethod def generate( self, system_prompt: str, user_prompt: str, max…

Hi All, Thank you for reporting this. The engineering team is aware of the empty response issue and is actively working on a fix. We will keep you updated as the fix is identified and rolled out.

Just tried it again this morning, All working again, for now :D. Thank you.

It will go down in another 7 hours. That is what has been happening for the past 3 days.

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

Gemini API

M_K August 23, 2025, 3:11pm 21

I appear to have it working by moving from end to end API to Vertex fixed it, I have posted more details in Gemini 2.5 Pro with empty response.text - #230 by Dumplin

Topic		Replies	Views
Gemini 2.5 Pro with empty response.text Gemini API gemini-20	238	23105	April 10, 2026
Possible Bug in Gemini 2.5 Pro Behavior empyty response Gemini API api , models , gemini_25_pro	3	403	January 5, 2026
Intermittent failure with FinishReason STOP Gemini API bug , gemini-25	2	900	September 15, 2025
Gemini 3.0 Pro preview with empty response.text Gemini API gemini , ground-search	9	1079	March 12, 2026
Gemini 2.5 Pro on Vertex sometimes returns empty string Gemini API prompt , gemini-2-5	8	815	November 6, 2025

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

Related topics