Gemini 4 Hydrogen API

Gemini 4 Hydrogen is the efficient model in Google's Gemini 4 series - made for high-volume work: agents, coding and bulk text processing, at a lower price than the stronger models in the series. It has one shared 1,048,576-token window for input, thinking and output. Thinking depth has three levels (low, medium - the default, high). It supports tool calls and JSON schema output. It answers with text. In Jantaris you call it with the same OpenAI SDK as every other model, without a separate Google account.

A single answer is capped at 32,768 tokens without streaming and 65,536 with streaming, and thinking counts toward that cap. For long answers set stream: true.

When the task gets harder - large codebases, multi-step reasoning - switch to Gemini 4 Carbon from the same series.

Best for

• Agents that take many cheap steps
• Classification, tagging and data extraction to JSON in large batches
• Summaries of long documents
• The first, cheap model in a cascade before Gemini 4 Carbon or Claude Opus 5.5

How to call it

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gemini-4-hydrogen",
    stream=True,
    messages=[{"role": "user", "content": "List the parties, amounts and deadlines in this contract as JSON."}],
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

FAQ

What is the Gemini 4 Hydrogen API price?

$0.81 / $4.05 per 1M tokens. You pay from one balance, only for the tokens you use.

How is it different from Gemini 4 Carbon?

Hydrogen has a lower token price and is made for a high number of requests. Pick Gemini 4 Carbon for harder code and complex reasoning. Both have the same context window.

How long can an answer be?

Up to 32,768 tokens without streaming and 65,536 with streaming, thinking included.

Does Hydrogen generate images or audio?

No, it answers with text only.

How to call Gemini 4 Hydrogen via API

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="gemini-4-hydrogen",
    messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)

curl https://jantaris.com/v1/chat/completions \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemini-4-hydrogen", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
  model: "gemini-4-hydrogen",
  messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);