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 …

I think it will get better, i.e. about 85-90% of requests will be processed smoothly in a day or two. I think this is because, firstly, the problem is completely undermining the product’s credibility, secondly, it is already starting to resonate, and thirdly, they will soon start losing money becaus…

I’m absolutely furious about this API mess that’s been dragging on for months it’s beyond frustrating that basic functionality has been broken for so long, with no end in sight. How can anyone seriously promote this as a leading or even viable option when the API is completely unusable week after we…

I have been using this model for 2 months. The issue is happening for 2 weeks. I dont know whether the issue has been going on for months.

It is hilarious how bad this is. More than half of my requests simply return something like this: {'candidates': [{'content': {'role': 'model'}, 'finishReason': 'STOP', 'index': 0}], 'usageMetadata': {'promptTokenCount': 2477, 'totalTokenCount': 2496, 'promptTokensDetails': [{'modality': 'TEXT', 't…

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 :frowning: I have posted here , looks like the same issue Gemini 2.5 Pro - Empty Response-Status 200 There are also these related links: …

[image] Aether1: And they unironically call this “Production ready”… yeah, a complete turn-off for gemini

After somebody (Mohamed but I can’t find his post so sorry to Mohamed and also credit to him) suggested using Pro 2.5 in Vertex AI instead of the end to end API, and it worked. I ran multiple requests with no issue, then flipped back and forwards to the end to end vs Vertex on Pro 2.5 and only the V…

Switching to Pro 2.5 via Vertex AI worked perfectly for me — no more failures. Appreciate the tip!

Subject: Bug Report: Gemini 2.5 Pro returns empty response via OpenAI-compatible API due to suspected silent tool call failure. Model: gemini-2.5-pro Environment: Accessed via an OpenAI-compatible API layer. Problem Description: When sending simple, open-ended prompts (e.g., “Hello”, “What shoul…

[image] Anderson_A_Perez: The issue is consistently resolved by adding “tool_choice”: “none” to the JSON request body. That is for the OpenAI-compatible API, right? Do you happen to know the alternative of that for the native Gemini REST API?

Gemini 2.5 Pro with empty response.text

Gemini API

Dumplin August 22, 2025, 5:01pm 230

yeah, a complete turn-off for gemini

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

Empty Response from AI running my clients

Gemini again started producing empty responses

Topic		Replies	Views
Empty response.text from Gemini 2.5 Pro, despite no safety and max_tokens issues Gemini API api , gemini-2-5	17	2579	November 24, 2025
Intermittent failure with FinishReason STOP Gemini API bug , gemini-25	2	859	September 15, 2025
Gemini 2.5 Pro on Vertex sometimes returns empty string Gemini API prompt , gemini-2-5	8	765	November 6, 2025
Gemini 3.0 Pro preview with empty response.text Gemini API gemini , ground-search	9	1001	March 12, 2026
Gemini 3.0 Pro Preview: Empty responses Gemini API bug , billing , gemini-3	6	670	February 3, 2026

Gemini 2.5 Pro with empty response.text

Related topics