Googlemessages

Gemini 4 Hydrogen (batch) API

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.

The model is built for everyday coding, debugging, rapid iterative development, codebase Q&A, agentic workflows, and exploring large repositories. It can batch-process parallel file reads and search calls, and it works standalone or in multi-model workflows with Gemini 4 Carbon and Gemini 4 Argon; in Orchestrator routing, Carbon plans and Hydrogen executes. The Antigravity SDK lets developers switch models programmatically.

Compared with Gemini 3.8 Flash, task completion is 2.5x faster and hallucinations are reduced by more than 5x. On complex graph, SQL, and data-intensive enterprise workflows it runs 2x to 2.8x faster while using 12% to 23% fewer tokens, and it produces output more than 30% faster when turning financial data into interactive models in Google Sheets. It uses the latest Gemini 4 security stack and is accessible in the Gemini API under the model name gemini-4-hydrogen.

Limited timeFree trial

Open Playground ↗Create API Key ↗Getting started →

Updated: Nov 13, 2026

MODEL ID

gemini-4-hydrogen:batch

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

Highlights

Four thinking levels: low, medium, high, xhigh
1M token context, 1,048,576 token output limit
Text, image, and video input
2.5x faster task completion than Gemini 3.8 Flash
Hallucinations reduced more than 5x vs Gemini 3.8 Flash
Latest Gemini 4 security stack

Providers

1 providers

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

Provider · Pricing details
					Uptime
	$0.75	$3.75	$0.0375	$0.0375

What $10 buys

Input: 13.3M tokens
Output: 2.7M tokens

Estimated from current input and output prices, before discounts.

Benchmarks

Artificial Analysis Intelligence Index
points at the default high setting
51
Artificial Analysis Intelligence Index
points at the xhigh setting
54
Terminal-Bench 4.1
57%
Vals Index
rank 6 of 37 models
68.49%
Tax Agent Bench
rank 1 of 85 models
52.30%
Vals Finance Index
rank 2 of 40 models
66.14%
Terminal-Bench 4.0
rank 11 of 64 models
54.04%
Vibe Code Bench
rank 13 of 128 models
87.78%

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:batch

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:batch",
  "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:batch",
  "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-hydrogen:batchPublic 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 (batch)?

Gemini 4 Hydrogen is Google's fast, high-efficiency model that replaces the Flash brand as the core of the Gemini 4 family. Released on 2026-11-12, it accepts text, image, and video input and produces text output, with a 1M token context window and an output limit of 1,048,576 tokens. It offers four thinking levels — low, medium, high (default), and xhigh — that adjust quality, latency, and cost to task complexity. The model is built for everyday coding, debugging, rapid iterative development, codebase Q&A, agentic workflows, and exploring large repositories. It can batch-process parallel file reads and search calls, and it works standalone or in multi-model workflows with Gemini 4 Carbon and Gemini 4 Argon; in Orchestrator routing, Carbon plans and Hydrogen executes. The Antigravity SDK lets developers switch models programmatically. Compared with Gemini 3.8 Flash, task completion is 2.5x faster and hallucinations are reduced by more than 5x. On complex graph, SQL, and data-intensive enterprise workflows it runs 2x to 2.8x faster while using 12% to 23% fewer tokens, and it produces output more than 30% faster when turning financial data into interactive models in Google Sheets. It uses the latest Gemini 4 security stack and is accessible in the Gemini API under the model name gemini-4-hydrogen.

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, image, and video input and returns text output.

What are the context and output limits?

It has a 1M token context window and an output limit of 1,048,576 tokens.

What tasks is it best suited for?

Everyday coding, debugging, rapid iterative development, codebase Q&A, agentic workflows, and exploring large repositories.

How does it differ from Gemini 4 Carbon and Gemini 4 Argon?

Hydrogen is the fast, high-efficiency core of the Gemini 4 family and replaces the Flash brand. In Orchestrator routing, Carbon plans and Hydrogen executes, and Hydrogen can be paired with Carbon or Argon in multi-model workflows.

How does it compare with Gemini 3.8 Flash?

Task completion is 2.5x faster and hallucinations are reduced by more than 5x. It also runs 2x to 2.8x faster on complex graph, SQL, and data-intensive enterprise workflows while using 12% to 23% fewer tokens.

Related models

Gemini 4 Hydrogen

Googlegemini-4-hydrogen

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

Everyday software developmentAgentic tool and API workflowsWriting, research and summariesData analysis and SQL pipelines

Context

1.049M

Max output

943.718K

Input tokens

$1.5 / 1M tokens

Output tokens

$7.5 / 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

Gemini 4 Carbon

Gemini 4 Carbon (batch)

Gemini 4 Argon

Gemini 3.8 Flash

Gemma 4 26B A4B (free)