Googlegemini-4-hydrogen
Google's fast, efficient Gemini 4 model for everyday coding and agentic workflows
$0.45/ 1M input tokens-70%$1.5official price
- 1M context
- Up to 64K output
- Effort low to xhigh
- Always thinks
- Reads images
- Modality
- Text
- Endpoint
- /v1/chat/completions
- Model ID
- gemini-4-hydrogen
- Provider
Gemini 4 Hydrogen API overview
Documented endpoint
Requests go to /v1/chat/completions, /v1/responses or /v1/messages, and the gateway converts each to Google's Gemini API. Google's own format, /v1beta/models/gemini-4-hydrogen:generateContent, works too.
Model provider
Gemini 4 Hydrogen is published by Google and is called through the API model ID gemini-4-hydrogen.
Output and limits
1,048,576-token context; up to 65,536 output tokens; text and images in, text out.
Gemini 4 Hydrogen API pricing
Gemini 4 Hydrogen is billed 70% below the official list price on every metered dimension below.
| Item | ArgoLink rate | Official price | You save |
|---|---|---|---|
| Input tokens | $0.45 / 1M tokens | -70% | |
| Cached input tokens | $0.0225 / 1M tokens | -70% | |
| Output tokens | $2.25 / 1M tokens | -70% |
Reasoning tokens are billed as output tokens.
Gemini 4 Hydrogen API reference
Quick start
Create an API key in the console, then use the Base URL, endpoint, and request body shown on this page.
curl -sS https://argolink.io/v1/chat/completions \
-H "Authorization: Bearer $ARGOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [{"role": "user", "content": "Explain what this model is good at in one sentence."}],
"stream": false
}'
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ARGOLINK_API_KEY"],
base_url="https://argolink.io/v1",
)
response = client.chat.completions.create(
model="gemini-4-hydrogen",
messages=[{"role": "user", "content": "Explain what this model is good at in one sentence."}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ARGOLINK_API_KEY,
baseURL: "https://argolink.io/v1",
});
const response = await client.chat.completions.create({
model: "gemini-4-hydrogen",
messages: [{ role: "user", content: "Explain what this model is good at in one sentence." }],
});
console.log(response.choices[0].message.content);
Protocols
Chat Completions
Recommended: converted to Google's Gemini API
OpenAI SDKs and OpenAI-compatible clients work as they are: the gateway converts each request to Google's Gemini API.
curl https://argolink.io/v1/chat/completions \
-H "Authorization: Bearer $ARGOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [{"role": "user", "content": "Compare optimistic and pessimistic locking in three bullet points."}],
"reasoning_effort": "high"
}'
curl https://argolink.io/v1/chat/completions \
-H "Authorization: Bearer $ARGOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "What does this chart show?"},
{"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0KGgo..."}}
]
}]
}'
| Field | Value |
|---|---|
messages | system, user, assistant and tool turns; a user turn may carry image_url parts, each a data URL |
thinking | always on; leave it out |
reasoning_effort | low · medium · high · xhigh |
max_completion_tokens | up to 65,536 |
stream | true streams server-sent events |
service_tier | not supported; leave it out |
max_completion_tokens counts thinking tokens too.
Responses and Anthropic Messages
Converted to Google's Gemini API
Codex, Claude Code and other clients that send these formats reach the same model: the gateway converts each request to Google's Gemini API.
curl https://argolink.io/v1/responses \
-H "Authorization: Bearer $ARGOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"input": "Compare optimistic and pessimistic locking in three bullet points."
}'
curl https://argolink.io/v1/messages \
-H "x-api-key: $ARGOLINK_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"max_tokens": 4000,
"messages": [{"role": "user", "content": "Compare optimistic and pessimistic locking in three bullet points."}]
}'
| Field | Value |
|---|---|
input | text and input_image parts; an image must be a data URL, because image links are dropped |
messages | text, tool and base64 image blocks; image URLs are dropped |
reasoning.effort | the same values as reasoning_effort |
output_config.effort | the same values; sent as medium when left out |
Gemini 4 Hydrogen full request parameters
| Parameter | Type | Requirement | What it does |
|---|---|---|---|
model | string | required | The catalog identifier for this page: gemini-4-hydrogen. |
messages | array | required | System, user, assistant and tool turns. User content may carry image_url parts, each a data URL. |
thinking | object | optional | Thinking: always on; leave it out. |
reasoning_effort | string | optional | Reasoning depth: low · medium · high · xhigh. |
max_completion_tokens | integer | optional | Caps the answer: up to 65,536. max_tokens works too. |
tools · tool_choice | array · string or object | optional | Function tools and how the model picks one. |
stream | boolean | optional | true streams chunks whose choices[].delta carry the text. |
service_tier | string | not supported | There is no faster tier for this model; leave it out. |
Gemini 4 Hydrogen API compared with similar models
| Model | Model ID | Provider | Rate | Best for |
|---|---|---|---|---|
| Gemini 4 Hydrogen | gemini-4-hydrogen | $0.45 / 1M input tokens | Google's fast, efficient Gemini 4 model for everyday coding and agentic workflows | |
| GPT-6 Astra | gpt-6-astra | OpenAI | $2.3 / 1M input tokens | OpenAI's most capable model, built for the hardest end-to-end work |
| GPT-5.6 Terra | gpt-5.6-terra | OpenAI | $0.46 / 1M input tokens | The GPT-5.6 model that balances intelligence and cost |
| GPT-5.6 Sol | gpt-5.6-sol | OpenAI | $0.92 / 1M input tokens | The GPT-5.6 flagship for complex professional work |
More models from this provider
- Gemini 3.8 FlashGoogle's fast, low-cost Gemini model for everyday text and image tasks$0.225 / 1M input tokens
- Gemini 4 ArgonGoogle's flagship Gemini model for complex reasoning, coding and long-context work$0.6 / 1M input tokens
- Gemini 4 CarbonGoogle's most capable Gemini reasoning model, built for complex software engineering, math and science$0.6 / 1M input tokens
Other models in this modality
- GPT-6 AstraOpenAI's most capable model, built for the hardest end-to-end work$2.3 / 1M input tokens
- GPT-5.6 TerraThe GPT-5.6 model that balances intelligence and cost$0.46 / 1M input tokens
- GPT-5.6 SolThe GPT-5.6 flagship for complex professional work$0.92 / 1M input tokens
- Claude Opus 5For complex agentic coding and enterprise work$1.75 / 1M input tokens
Gemini 4 Hydrogen API FAQ
How do I call Gemini 4 Hydrogen?
Create an API key in the console and POST https://argolink.io/v1/chat/completions with model set to gemini-4-hydrogen and your key in the Authorization header as a Bearer token. /v1/responses and /v1/messages work too; the gateway converts every request to Google's Gemini API.
How much does Gemini 4 Hydrogen cost?
$0.45 per million input tokens and $2.25 per million output tokens, 70% below the official rates. Cached input costs $0.0225 per million. Reasoning tokens are billed as output tokens.
What are Gemini 4 Hydrogen's context and output limits?
1,048,576-token context; up to 65,536 output tokens; text and images in, text out.
How do I control Gemini 4 Hydrogen's reasoning?
It always thinks. Set reasoning_effort to low, medium, high or xhigh.
Can Gemini 4 Hydrogen read images?
Yes: send them as image_url parts, each a data URL, on /v1/chat/completions. Image links are dropped on every format, so send each image inside the request.