How much does Gemini 4 Carbon cost?

Until November 30, 2026: $2 per million input tokens and $10 per million output tokens, thinking tokens included. From December 1, 2026: $4 and $20. Cached input is $0.10 per million tokens during the offer and $0.20 after it. There is no monthly fee.

What is the difference between Gemini 4 Carbon and Gemini 4 Argon?

Carbon is built on Argon and is Google's stronger model: it scores 59 on the Artificial Analysis Intelligence Index against Argon's 50, at the same price.

How do I use Gemini 4 Carbon from inside Iran?

Create a Hormouz account and an API key, then call the model through Hormouz's OpenAI-compatible API. You pay in rial from your Hormouz balance; no foreign card or circumvention tool is needed.

Does Gemini 4 Carbon work with my OpenAI code?

Yes. Point the base URL of your OpenAI SDK at Hormouz, use your Hormouz key and set the model to google/gemini-4-carbon. Nothing else changes.

What context window does Gemini 4 Carbon have?

1,048,576 tokens of context, with answers of up to 32,768 tokens. It takes text, image, audio, video and file input.

Gemini 4 Carbon: AI model

Gemini 4 Carbon is Google's most capable reasoning model, built on Gemini 4 Argon, with a 1M-token context window and half-price introductory pricing until November 30, 2026. Reachable from inside Iran through Hormouz.

Context window:: 1,048,576 tokens
Input:: $2/1M tokens
Output:: $10/1M tokens
Discount:: −50%
Type:: text, audio, image, video

Vision
Tools
Streaming
Long context

Thinking levels: Always thinks · high · medium · low

Gemini 4 Carbon is Google's most capable reasoning model. Google announced it on October 28, 2026 as the successor to Gemini 4 Argon and opened it to paid API developers in November 2026. It is built for complex software engineering, deep mathematical and scientific problem solving, high factual accuracy and autonomous agents that work through many steps. On the Artificial Analysis Intelligence Index it scores 59, against 50 for Gemini 4 Argon.

It accepts text, image, audio, video and file input and returns text. The context window is 1,048,576 tokens and one response can be up to 32,768 tokens long. It supports tool calling, structured JSON output and streaming, and you choose how hard it thinks with the reasoning effort setting: low, medium or high. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, use a Hormouz key, and existing OpenAI SDK code runs unchanged.

Google launched it at the same introductory price as Argon. Until November 30, 2026 it costs $2 per million input tokens and $10 per million output tokens, thinking tokens included; from December 1, 2026 the price is $4 and $20. Cached input costs $0.10 per million tokens during the offer and $0.20 after it, and caching is automatic. There is no monthly fee: you pay only for the tokens you use, from the same Hormouz balance as every other model.

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-4-carbon",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Google
Type	Text, Audio, Image, Video
Context window	1,048,576 tokens
Pricing	Previous price: $4 / $20 per MDiscounted price: $2 / $10 per M−50%
API	Chat Completions
Capabilities	Streaming · Vision · Tools

Benchmarks

Intelligence Index

Better than 96% of models we compared

Source: Artificial Analysis

Code example

cURL

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-4-carbon",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="google/gemini-4-carbon",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "google/gemini-4-carbon",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Gemini 4 Carbon API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Gemini 4 Carbon and nearly 700 other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account Buy Gemini API access, paid in rial

Use via Hormouz

Connect to this model and nearly 700 others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Gemini 4 Carbon cost?: Until November 30, 2026: $2 per million input tokens and $10 per million output tokens, thinking tokens included. From December 1, 2026: $4 and $20. Cached input is $0.10 per million tokens during the offer and $0.20 after it. There is no monthly fee.
What is the difference between Gemini 4 Carbon and Gemini 4 Argon?: Carbon is built on Argon and is Google's stronger model: it scores 59 on the Artificial Analysis Intelligence Index against Argon's 50, at the same price.
How do I use Gemini 4 Carbon from inside Iran?: Create a Hormouz account and an API key, then call the model through Hormouz's OpenAI-compatible API. You pay in rial from your Hormouz balance; no foreign card or circumvention tool is needed.
Does Gemini 4 Carbon work with my OpenAI code?: Yes. Point the base URL of your OpenAI SDK at Hormouz, use your Hormouz key and set the model to google/gemini-4-carbon. Nothing else changes.
What context window does Gemini 4 Carbon have?: 1,048,576 tokens of context, with answers of up to 32,768 tokens. It takes text, image, audio, video and file input.

Updated 2026-11-11