Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • Best Browsers 2026: Rankings and Top Lists
  • AI Browser Guides and Resources
  • Browser Comparisons: Head-to-Head Guides
  • Browser Reviews and Explainers
  • Browser Alternatives
  • Browser Directory: Guides by Browser
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Productivity Resources
  • SillyTavern Model Guides and Presets

Popular Guides

  • Best Browsers 2026: Top 10 Ranked & Compared
  • Best Free AI Browsers 2026: Plans & Prices Compared
  • Rabbit Browser: What It Is & Why Tabbit Is Better
  • Firefox vs Chrome 2026: Privacy, RAM & Speed Compared
  • Best Lightweight Browsers 2026: 7 Tested for RAM & Speed
  • AI Browser List 2026: 10 Browsers Compared
  • Neobrowser: Norton Neo, Download & Alternatives
  • Edge vs Chrome 2026: Speed, RAM & Battery Tested
  • Best Internet Browser for Android 2026
  • Best AI Browser 2026: Top 9 Tested & Ranked

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
English
简体中文English
Showcases & prompts
OfficialGemini 4 Hydrogen

Google AI Studio: Gemini 4 Hydrogen's Four Thinking Levels

Original source

Google AI Studio Gemini API documentation

AuthorGoogle

Tabbit curation2026-11-16

Read original

One-sentence takeaway

Hydrogen defaults to high. Set generation_config.thinking_level to choose among low, medium, high, and xhigh, then use the same task set to find the lowest level that meets your quality requirements.

Use cases

  • Good for: Choosing a thinking level for Gemini 4 Hydrogen API requests and diagnosing quality, latency, token usage, or output truncation issues.

  • Not suitable for: Comparing the overall capabilities of different models or different task sets.

  • Applicable model version: gemini-4-hydrogen.

  • Applicable client, agent, or API: Gemini API Interactions API; the example uses the Google Gen AI JavaScript SDK.

  • Recommended thinking level and parameters: Start with the default high for generally complex tasks. Try medium or low to meet latency and cost requirements. Raise the level to xhigh only for difficult, multi-step tasks where high does not meet the quality bar. Hydrogen does not support minimal.

Ready-to-use content

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});
const interaction = await client.interactions.create({
  model: "gemini-4-hydrogen",
  input: "Review this retry queue code for race conditions and provide a corrected implementation.",
  generation_config: {
    thinking_level: "high",
  },
});
console.log(interaction.output_text);

Set thinking_level to low, medium, or xhigh to switch levels. If you omit this field, Hydrogen defaults to high. In REST requests, the corresponding field is under generation_config:

{
  "model": "gemini-4-hydrogen",
  "input": "Review this retry queue code for race conditions and provide a corrected implementation.",
  "generation_config": { "thinking_level": "xhigh" }
}

Test or workflow steps

What each level means (as recommended in Google's documentation):

LevelTasks to tryExpected trade-offs
lowQuick Q&A, high-throughput processing, latency-sensitive tool callsFewest tokens and lowest latency; can still handle agent tasks
mediumInteractive coding, real-time UI prototyping, response-time-sensitive chatLower token usage and response time
highComplex coding, agent execution, tool calls, multimodal knowledge tasksHydrogen default; balances quality and speed
xhighDifficult, multi-step coding or agent problems that high cannot solveDeepest reasoning, with more token usage and higher latency; may overthink simple extraction tasks

Use the following process to avoid mistaking truncation for a lack of capability at lower levels:

  1. Keep the same set of Hydrogen inputs and change only thinking_level each time. Cover simple extraction, interactive coding, and complex multi-step problems.

  2. For the initial side-by-side comparison, allow a generous max_output_tokens budget. Record task success rate, total time, and token usage at each level, then choose the lowest level that meets the quality bar.

  3. For JSON and text extraction, compare high and xhigh separately. Check whether the extra reasoning improves results, increases latency or token usage, or exceeds the output budget.

  4. Retest under the target production limit: max_output_tokens is a hard truncation limit that includes thinking tokens. If the budget runs out during reasoning, the response returns as incomplete, and the final text may be truncated or empty. If your goal is only to reduce cost or latency, lower the thinking level first; do not set the output limit too low.

  5. Record total_thought_tokens and completion status to distinguish a normal answer, an exhausted reasoning budget, and valid output that is too long. If needed, raise the limit and rerun to confirm whether truncation occurred.

Steps 1–5 are validation recommendations based on the official documentation. Google recommends evaluating all four levels with a high max_output_tokens limit, then choosing the lowest level that meets your quality requirements.

Original evidence and data

  • The model-level table marks high as Hydrogen's default and lists low, medium, high, and xhigh as supported levels. The documentation says Gemini 4 does not support minimal.

  • Official descriptions: low uses the fewest tokens and has the lowest latency; medium is for interactive coding and latency-sensitive tasks; high is the recommended default for most Hydrogen tasks; xhigh is for difficult, multi-step problems that high cannot handle.

  • Google warns that xhigh increases latency and token usage, and may overthink simple text or JSON extraction or exhaust max_output_tokens.

  • max_output_tokens applies to thinking tokens and final output combined and is a hard infrastructure-enforced limit. Exhausting it during the thinking phase marks the response as incomplete and may produce truncated or empty output, but the thinking tokens already generated are still billed.

  • The Interactions API can provide total_thought_tokens in its response. Enabling thought summaries can expose reasoning summaries, but these may be empty or missing, so they should not be the sole indicator of whether reasoning took place.

Scope and limitations

The quality, latency, and token trade-offs for each level are described qualitatively by Google; the documentation does not provide fixed token counts or latency guarantees for each level. Measure results using your target inputs, output limits, and service environment. Do not generalize the result of a single task to all tasks.

Reproduction notes

On 2026-11-16, the original documentation was opened through Tabbit, and the “Controlling thinking” and “Token limits and max_output_tokens” sections, along with Hydrogen's Interactions API configuration example, were checked. The testing steps in this note are reproduction recommendations, not benchmark results published by Google.

Curated by Tabbit

Prompts and showcases are summarized from public sources and Tabbit editorial notes. Check the original licensing and intended use before copying it.

Gemini 4 Hydrogen

Use in Tabbit

Gemini 4 Hydrogen

Related showcases & prompts

OfficialGoogle AI for Developers (Gemini API documentation)

Google Gemini API: Gemini 4 Hydrogen Model Configuration

OfficialGoogle AI Studio documentation

Google AI Studio: Migrating from Gemini 3.8 Flash to Gemini 4 Hydrogen

OfficialGoogle AI Studio Gemini API documentation

Google AI Studio: Locate Content in Long Videos with Gemini 4 Hydrogen

OfficialOpenRouter

OpenRouter: Gemini 4 Hydrogen Model Routing Configuration

Gemini 4 Hydrogen

Related reviews

OfficialGoogle DeepMind2026-11-12

Google DeepMind's Official Capability Benchmarks: Gemini 4 Hydrogen

MediaAI IQ

Gemini 4 Hydrogen: AI IQ Scores and Benchmark Coverage

MediaPlotly Blog2026-11-12

Plotly Data Analytics Benchmark: Gemini 4 Hydrogen Scores 43/43

MediaArena WebDev Leaderboard2026-11-14

Gemini 4 Hydrogen (High): Arena WebDev Leaderboard