# \#gen-ai
**URL:** https://discuss.ai.google.dev/tag/gen-ai/445.md
[Latest](https://discuss.ai.google.dev/latest.md) · [Categories](https://discuss.ai.google.dev/categories.md) · [Tags](https://discuss.ai.google.dev/tags.md)
---
## [Gemini 2.5 Pro (paid, with API key) errors 100% of the time when token count is over 131k](https://discuss.ai.google.dev/t/gemini-2-5-pro-paid-with-api-key-errors-100-of-the-time-when-token-count-is-over-131k/106600)
**Author:** [@Steven\_Waterman](https://discuss.ai.google.dev/u/Steven_Waterman)\
**Replies:** 8\
**Last updated:** [December 29, 2025, 1:20pm UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-paid-with-api-key-errors-100-of-the-time-when-token-count-is-over-131k/106600 "2025-12-29T13:20:47Z")
We are using Gemini 2.5 heavily in production and as of this morning, it stopped working. Any time we go over 131k tokens, we get the error below: Status 400, Bad Request. The input token count (…) exceeds the maximum …
---
## ['NoneType' object has no attribute 'parts'](https://discuss.ai.google.dev/t/nonetype-object-has-no-attribute-parts/110861)
**Author:** [@Ankan](https://discuss.ai.google.dev/u/Ankan)\
**Replies:** 1\
**Last updated:** [December 3, 2025, 7:21am UTC](https://discuss.ai.google.dev/t/nonetype-object-has-no-attribute-parts/110861 "2025-12-03T07:21:41Z")
this is the error i am facing while generating video from image from nano banana and veo3 preview models.. INFO:httpx:HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:gen…
---
## [Code Execution - ValueError: Chunk too big](https://discuss.ai.google.dev/t/code-execution-valueerror-chunk-too-big/97432)
**Author:** [@Firley\_Company](https://discuss.ai.google.dev/u/Firley_Company)\
**Replies:** 3\
**Last updated:** [September 29, 2025, 6:53pm UTC](https://discuss.ai.google.dev/t/code-execution-valueerror-chunk-too-big/97432 "2025-09-29T18:53:18Z")
I have an issue with code execution. I am using a fastAPI server with the python google-genai sdk. The app is designed to use code execution, with some use cases being to generate images and graphs. I followed the Google…
---
## [Failed to create file. Upload URL was not returned in the create file response](https://discuss.ai.google.dev/t/failed-to-create-file-upload-url-was-not-returned-in-the-create-file-response/94476)
**Author:** [@Laith\_Mihyar](https://discuss.ai.google.dev/u/Laith_Mihyar)\
**Replies:** 4\
**Last updated:** [August 21, 2025, 2:16am UTC](https://discuss.ai.google.dev/t/failed-to-create-file-upload-url-was-not-returned-in-the-create-file-response/94476 "2025-08-21T02:16:03Z")
I’m using the com.google.genai:google-genai:1.9.0 SDK in a Spring Boot Java project. I’m trying to upload a file, but I keep encountering the following error: “Failed to create file. Upload URL was not returned in the …
---
## [Doom Loop - Frequency Penalty - 2.5 Flash](https://discuss.ai.google.dev/t/doom-loop-frequency-penalty-2-5-flash/94446)
**Author:** [@epreisz](https://discuss.ai.google.dev/u/epreisz)\
**Replies:** 4\
**Last updated:** [July 18, 2025, 5:56pm UTC](https://discuss.ai.google.dev/t/doom-loop-frequency-penalty-2-5-flash/94446 "2025-07-18T17:56:55Z")
My code is fairly structured and it’s quite a frequent occurrence for my prompt to get stuck in a doom loop of repeating itself. I’ve experienced this in other non-Google models, but was able to resolve it by setting a s…
---
## [ThinkingConfig validation error with thinking\_budget parameter in Python SDK](https://discuss.ai.google.dev/t/thinkingconfig-validation-error-with-thinking-budget-parameter-in-python-sdk/93322)
**Author:** [@Maiwenn](https://discuss.ai.google.dev/u/Maiwenn)\
**Replies:** 2\
**Last updated:** [July 14, 2025, 2:36pm UTC](https://discuss.ai.google.dev/t/thinkingconfig-validation-error-with-thinking-budget-parameter-in-python-sdk/93322 "2025-07-14T14:36:00Z")
I’m getting a Pydantic validation error when trying to use the thinking\_budget parameter with the Google GenAI Python SDK. The error occurs even when following the official documentation example. Issue: The ThinkingConf…