Googlemessages

Gemini 4 Hydrogen API

Gemini 4 Hydrogen is Google's fast, cost-efficient daily-driver model with a 1M-token context, multimodal input and four adjustable thinking levels.

For software work, Gemini 4 Hydrogen answers questions about a codebase, finds and fixes bugs, and makes focused, surgical edits without rewriting unrelated files. When exploring large repositories it batches file reads and search calls in parallel. It also breaks goals down step by step and executes tasks, which suits agentic workflows that automate work across multiple tools and APIs, as well as writing, research, data analysis and enterprise pipelines involving complex graphs and SQL.

Gemini 4 Hydrogen completes tasks 2.5x faster than Gemini 3.8 Flash, runs 2x to 2.8x faster and uses 12% to 23% fewer tokens. Deep reasoning tasks are intended to be delegated to Gemini 4 Carbon or Gemini 4 Argon, and it pairs with them in a multi-model setup.

Limited timeFree trial

Open Playground ↗Create API Key ↗Getting started →

Updated: Nov 13, 2026

MODEL ID

gemini-4-hydrogen

Context: 1.049M
Max output: 943.718K
Recommended API: messages
Input: audio / file / image / text / video
Output: text

Highlights

1M-token context window
Four thinking levels, low to extra high
Text, image and other data inputs
2.5x faster task completion than Gemini 3.8 Flash
12% to 23% fewer tokens used
Surgical code edits without unrelated rewrites

Providers

5 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details

$1.5	$7.5	$0.075	$0.075
$0.75	$3.75	$0.0375	$0.0375
$1.5	$7.5	$0.075	$0.075
$2.7	$13.5	$0.135	$0.135
$2.7	$13.5	$0.135	$0.135

Pricing details

What $10 buys

Input: 6.7M tokens
Output: 1.3M tokens

Estimated from current input and output prices, before discounts.

Benchmarks

Artificial Analysis Intelligence Index
At the default thinking level, above Gemini 4 Argon.
54
Agentic overreach reduction
Maximum reduction achieved.
81%
Under-service reduction
Maximum reduction achieved.
79%
Erroneous action and shortcut reduction
Measured on tool use and coding evaluations.
12x
Agent integrity honesty rate
Result on an internal agent integrity evaluation.
96.7%
Chain-of-thought readability
Based on more than 200,000 audited turns.
99.9%
Gray Swan IPI
Resistance to indirect prompt injection attacks, or higher.
2.3x
HealthBench Pro false refusal rate
Below 0.4%.
0.4%

Scores as published by the model provider.

Reasoning

Default effort: medium
Always enabled: Yes
Available effort levels: xhigh / high / medium / low

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open Playground Create API Key

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

gemini-4-hydrogen

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "gemini-4-hydrogen",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-4-hydrogen",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription

modelstringgemini-4-hydrogenPublic model ID to call.

max_tokensinteger—Maximum generated tokens.

messagesarray—Conversation messages for Chat Completions.

seed———

stop———

toolsarray—Tool calling definitions following compatible schema.

top_p———

reasoning———

temperaturenumber—Controls response variety when supported.

tool_choicestring or object—Controls whether a tool should be called.

response_formatobject—Request structured output when supported.

reasoning_effort———

include_reasoning———

structured_outputs———

Frequently asked questions

What is Gemini 4 Hydrogen?

Gemini 4 Hydrogen is Google's successor to Gemini 3.8 Flash, built as a fast and cost-efficient daily driver. It accepts text, image and other data formats, carries a 1M-token context window, and offers four adjustable thinking levels ranging from low to extra high. In the Gemini app it calls appropriate tools and follows user instructions closely, and it can pull relevant context from uploaded files, Gmail, Google Drive, Airtable and Dropbox. For software work, Gemini 4 Hydrogen answers questions about a codebase, finds and fixes bugs, and makes focused, surgical edits without rewriting unrelated files. When exploring large repositories it batches file reads and search calls in parallel. It also breaks goals down step by step and executes tasks, which suits agentic workflows that automate work across multiple tools and APIs, as well as writing, research, data analysis and enterprise pipelines involving complex graphs and SQL. Gemini 4 Hydrogen completes tasks 2.5x faster than Gemini 3.8 Flash, runs 2x to 2.8x faster and uses 12% to 23% fewer tokens. Deep reasoning tasks are intended to be delegated to Gemini 4 Carbon or Gemini 4 Argon, and it pairs with them in a multi-model setup.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

What input types does Gemini 4 Hydrogen support?

It accepts text input, image input and other data formats input, and supports multimodal understanding and embodied reasoning.

How large is the context window?

Gemini 4 Hydrogen offers a 1M-token context window, which helps when exploring large repositories or long documents.

What is it best suited for?

It is optimized for speed and cost efficiency as a daily driver: everyday coding, agentic workflows across tools and APIs, writing and research, and data-heavy enterprise workflows. Deep reasoning tasks are intended to be delegated to Gemini 4 Carbon or Gemini 4 Argon.

How does it differ from the other Gemini 4 models?

Gemini 4 Hydrogen is positioned as the successor to Gemini 3.8 Flash and is optimized for speed and cost, while deep reasoning is meant to be handled by Gemini 4 Carbon or Gemini 4 Argon. It can be paired with those models in a multi-model setup.

Does it have adjustable reasoning effort?

Yes, it offers four adjustable thinking levels, from low to extra high.

Related models

Gemini 4 Hydrogen (batch)

Googlegemini-4-hydrogen:batch

Gemini 4 Hydrogen is Google's fast, high-efficiency core of the Gemini 4 family, replacing the Flash brand with four thinking levels and multimodal input.

Everyday codingDebuggingRapid iterative developmentCodebase Q&A

Context

1.049M

Max output

943.718K

Input tokens

$0.75 / 1M tokens

Output tokens

$3.75 / 1M tokens

Gemini 4 Carbon

Googlegemini-4-carbon

Gemini 4 Carbon is Google's strongest frontier model, built on Gemini 4 Argon for long-horizon agentic workflows, cybersecurity, scientific reasoning, and complex knowledge work.

Cybersecurity vulnerability discovery and patchingLong-horizon agentic workflowsLarge-scale codebase migrationsScientific reasoning and research

Context

1.049M

Max output

943.718K

Input tokens

$4 / 1M tokens

Output tokens

$20 / 1M tokens

Gemini 4 Carbon (batch)

Googlegemini-4-carbon:batch

Gemini 4 Carbon is Google's multimodal frontier model for long-horizon agentic work, with 1 million token context and adjustable reasoning effort.

Long-horizon agentic engineeringAdvanced coding and full-stack developmentDeep financial research and Excel modelsCyber defense and vulnerability discovery

Context

1.049M

Max output

943.718K

Input tokens

$2 / 1M tokens

Output tokens

$10 / 1M tokens

Gemini 4 Argon

Googlegemini-4-argon

Google's Gemini 4 Argon is a frontier model with a 1,048,576-token context window, multimodal input support, and top scores on 14 of 18 internal benchmarks.

Software engineering and codingFinance ledger reconciliationLegal case law reviewCybersecurity defense automation

Context

1.049M

Max output

943.718K

Input tokens

$4 / 1M tokens

Output tokens

$20 / 1M tokens

Gemini 3.8 Flash

Googlegemini-3.8-flash

Gemini 3.8 Flash is Google's most intelligent Flash model, a reasoning model with 1,000,000-token context and multimodal input for long-horizon agents and enterprise workflows.

Long-horizon software engineeringAutonomous agentsComplex enterprise workflowsMulti-step orchestration

Context

1.049M

Max output

65.536K

Input tokens

$1.5 / 1M tokens

Output tokens

$7.5 / 1M tokens

Gemma 4 26B A4B (free)

Googlegemma-4-26b-a4b-it:free

Gemma 4 26B A4B is an open-weight multimodal Mixture-of-Experts model from Google DeepMind with 26B total and 4B active parameters, a 256K token context, and support for text, image, and video input.

Coding assistance in IDEsAgentic workflows and tool useScientific and mathematical problem solvingDocument parsing and OCR

Context

262.144K

Max output

32.768K

Input tokens

$0 / 1M tokens

Output tokens

$0 / 1M tokens

Highlights

Performance history+

What $10 buys

Benchmarks

Reasoning

Quick Start

Get your API key

Make your first request

Using third-party SDKs

Enable streaming

Endpoint

Parameters

Frequently asked questions

Related models

Gemini 4 Hydrogen (batch)

Gemini 4 Carbon

Gemini 4 Carbon (batch)

Gemini 4 Argon

Gemini 3.8 Flash

Gemma 4 26B A4B (free)