Hi, I’m working on a search engine that send the found documents to Flash model for summarization. When I retrieve the docs and send them to the model I get: google.api_core.exceptions.InvalidArgument: 400 The input token count (34108) exceeds the maximum number of tokens allowed (32767). By the …

[image] KonradPs: It works OK when grounding is not used. Hi @KonradPs , Have you tried with “2.0-flash-exp” ?? Is it the same case with this model also??

I only tested 1.5-flash. It seems that when using grounding the token limit is different compared to ‘non-grounded’ use.

Hey @KonradPs , Grounding is not supported for non-text input with 1.5 models. Without retrieval tool it will work. Use “2.0-flash-exp” latest model with grounding if you want to upload files or multimodal input. You can also try this in Vertex AI studio or in Google AI studio, it will throw error. …

yes the tokens are limited for 2.0-flash-exp that is 32767

If anyone has similar issues with Gemini 2.0 Flash with structured output, I solved the issue by adding more tokens(!). By adding ~2000 additional tokens to my system prompt, marked as padding to not confuse the model, the requests worked again!

Token limit error (1.5 Pro and Flash)

Gemini API

Hugo_Adame December 30, 2024, 5:25am 6

Escriba o pegue el código aquí**texto fuerte

> Cita en bloque

**

Topic		Replies	Views
Incorrect gemini-2.5-pro input token limit response Gemini API api , models	4	635	January 13, 2026
Input token limits after Finetuning Gemini API gemini-15 , fine-tuning	3	258	February 20, 2025
Help with Error "The input token count (35868) exceeds the maximum number of tokens allowed (32768)."}" Gemini API gemini-15 , api	12	953	March 20, 2025
Payload Size Limit Error with embed_content API Gemini API ai-studio , api , models	5	982	January 9, 2025
Gemini 3.1 Pro Preview Throwing Token Rate Limit error of 131072 tokens via Vertex API? Gemini API vertexai , gemini-3	3	302	April 3, 2026

Token limit error (1.5 Pro and Flash)

Related topics