Gemini 4 Hydrogen

Google Gemini 4 model for everyday coding, agentic workflows and multimodal reasoning. Shared 1048576-token input, thinking and output context; 65536-token synchronous output limit.

Input / output price: $1.50 / $7.50 per 1M
Context: 1M tokens
Released: Nov 12, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "google_gemini_ai/gemini-4-hydrogen".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="google_gemini_ai/gemini-4-hydrogen",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "google_gemini_ai/gemini-4-hydrogen",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "google_gemini_ai/gemini-4-hydrogen",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Google Gemini AI`google_gemini_ai/gemini-4-hydrogen`	1M	$1.50/M	$7.50/M	$0.075/M
OpenRouter`openrouter/google/gemini-4-hydrogen`	1M	$1.50/M	$7.50/M	$0.075/M

Is a provider down? OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $1.50 per 1M
Average output: $7.50 per 1M
Average cache read: $0.07 per 1M
Average cache write: $0.08 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.50/MGoogle Gemini AI and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

1195tokens/sacross providers

Faster than 97% of the other 560 models on the gateway

Time to first token

Lower is better

4.2sacross providers

Faster than 22% of the other 136 models on the gateway

Response latency

Lower is better

7.5sacross providers

Faster than 23% of the other 650 models on the gateway

Benchmarks

10 published scores from 4 sources, each linked to where it was published.

Published scores

Benchmark	Score	Source	Published
Terminal-Bench 4.0Vals AI	54%	Vals AI	Nov 13, 2026
FrontierSWE V2Proximal Labs	53.1%	Proximal Labs	Nov 13, 2026
Terminal-Bench Science 0.1Google	51.4%	Google	Nov 12, 2026
SWE-sweepGoogle	13.5%	Google	Nov 12, 2026

Benchmark	Score	Source	Published
OSWorld-2.1 (Offline subset)Google	77.6%	Google	Nov 12, 2026
AutomationBench-AAGoogle	76.1%	Google	Nov 12, 2026
Agents' Last Exam v1.1Google	71.6%	Google	Nov 12, 2026

Benchmark	Score	Source	Published
HLE-DiamondGoogle	58.8%	Google	Nov 12, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1704 Elo · #9 of 120	LMArena	Nov 11, 2026
LMArena EloLMArena	1490 Elo · #13 of 181	LMArena	Nov 11, 2026

Apps

Use Gemini 4 Hydrogen in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Gemini 4 Hydrogen FAQ

Short answers, built from the data on this page.

Gemini 4 Hydrogen is a model from Google Gemini AI, released on Nov 12, 2026. Google Gemini 4 model for everyday coding, agentic workflows and multimodal reasoning. Shared 1048576-token input, thinking and output context; 65536-token synchronous output limit.

On the Respan gateway, Gemini 4 Hydrogen costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on every provider, after gateway discounts.

Gemini 4 Hydrogen is available through 2 providers: Google Gemini AI and OpenRouter.

Gemini 4 Hydrogen accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "google_gemini_ai/gemini-4-hydrogen". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 4 Hydrogen has 10 published benchmark scores, including Terminal-Bench 4.0 54%, OSWorld-2.1 (Offline subset) 77.6%, and HLE-Diamond 58.8%. Each score links to where it was published; the data is collected by Respan.