Gemini 2.5 Pro using thought tokens but intermittently not returning thoughts

We’re finding that intermittently, but increasingly, our gemini 2.5 pro model results are returning output which does not contain any thoughts. It shows it has used some of the thinking budget (thoughtsTokenCount), but will just return the text output without its reasoning. Anyone else running into this issue, have you resolved it?

The config uses:

"thinkingConfig": {

    "includeThoughts": true,
    "thinkingBudget": 20000

}

Hi @Steff,
Welcome to the AI forum! Thanks for reporting this issue.
We are not able to reproduce this issue. Can you please confirm if you are still facing this issue. If possible, provide the code snippet, so that we can identify the cause.