PulseAugur
EN
LIVE 15:52:00

Gemini API experiment shows thinkingBudget: 0 still uses thinking tokens

An experiment with the Gemini API revealed that setting a `thinkingBudget` to 0 did not prevent the model from using thinking tokens, contrary to documentation for Firebase AI Logic. The API accepted requests with a `thinkingBudget` of 0, 1024, and 8192, and the `gemini-4-hydrogen` model consistently used over 1,200 thinking tokens even with a budget of 0. This suggests that the `thinkingBudget` parameter acts as a suggestion rather than a strict limit for this model and API. AI

IMPACT Developers should verify LLM configurations and not assume parameters like `thinkingBudget` are strict limits without explicit documentation.

RANK_REASON The item describes an unexpected behavior of an API parameter, which is a specific product observation rather than a new model release or significant industry event.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Gemini API experiment shows thinkingBudget: 0 still uses thinking tokens

How we ranked this

Signal score
51 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes an unexpected behavior of an API parameter, which is a specific product observation rather than a new model release or significant industry event.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Prikshit ·

    Gemini Accepted "thinkingBudget: 0". So Why Was It Still Thinking?

    <p><em>An unexpected Gemini API result, a small experiment with reasoning tokens, and a lesson about verifying LLM behavior before production.</em></p> <h2> 1. The Unexpected Result </h2> <p>Imagine configuring an AI model to minimize its reasoning effort. You set:<br /> </p> <di…