Gemini 4 Carbon API

Q: What is the Gemini 4 Carbon model ID?

Use google/gemini-4-carbon as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

Debug multi-step code, review security and run long agent workflows with Google's Gemini 4 Carbon

Modalities: Image, TextText
In / Out price: $2.33/$11.64per 1M
Context window: 1.05M tokens
Released: Nov 10, 2026

Gemini 4 Carbon overview

Gemini 4 Carbon by Google

Google built Gemini 4 Carbon for complex software engineering, scientific reasoning, cybersecurity defense and long-horizon agentic workflows. Google lists text, image, audio, video and PDF input for the model.

Gemini 4 Carbon specs

Model ID: google/gemini-4-carbon
Developer: Google
Context window: 1,048,576 tokens
Max output: 65,536 tokens
Input: Image, Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Expect long reasoning on hard prompts

Google says Gemini 4 Carbon uses more tokens than Gemini 4 Argon to reason deeply, explore thoroughly and run extended verification loops. On a difficult prompt, the reasoning phase can therefore take a large share of the tokens you generate.

Log token usage on a sample of your real requests before you scale a workload.

Set reasoning effort first

The reasoning effort option accepts low, medium or high. Lowering it gives faster responses and fewer tokens spent on reasoning.

Start with medium. Move to high when multi-step coding or analysis answers fall short. Move to low for simple requests where speed matters more than depth.

Carbon or Argon

Google recommends Gemini 4 Carbon for complex multi-step coding and debugging, for open-ended scientific research and discovery, and for other tasks that test the limits of model intelligence. Gemini 4 Argon is Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.

Run the same few of your hardest prompts through both models. Compare the answers and the reasoning tokens each one spends.

Use cases

Debug a multi-step failure across several files and propose a fix with verification steps.

Review code for vulnerabilities and draft patches for the issues found.

Work through an open-ended scientific question using excerpts and figures supplied as text and images.

Run a long-horizon agent workflow that plans, acts and checks its own results.

Capabilities

File input
Reasoning
Streaming
Structured outputs
Function calling
Vision

Gemini 4 Carbon benchmarks by Artificial Analysis

See how Gemini 4 Carbon compares in intelligence, generation speed and cost per task. Data retrieved Nov 9, 2026.

Intelligence#2 / 6360Index v5.0 Speed#116 / 21999.7Output tokens / second Cost per task#51 / 54$7.76USD / benchmark task Terminal-Bench 4.0#2 / 15465.2%Score

Intelligence

Index v5.0

Speed

Output tokens / second

Cost per task

USD / benchmark task

Benchmark results

Compare 5 models available on AI/ML API across 2 independent benchmarks.

Terminal-Bench 4.0

Agentic tasks completed in a command-line environment.

Gemini 4 Carbon API pricing

Gemini 4 Carbon pricing in US dollars
Usage	Price	Unit
Input	$2.33	1M tokens
Output	$11.64	1M tokens
Cached input	$0.1164	1M tokens

Prices from the AI/ML API price list, checked on Nov 10, 2026.

Gemini 4 Carbon vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Gemini 4 Carbon	$2.33	$11.64
Gemini 3.8 Flash	$0.75	$3.75
Gemini 3.7 Flash	$0.75	$3.75
Gemini 3.6 Flash	$1.5	$7.5
Gemini 4 Argon	$2	$10

How to use the Gemini 4 Carbon API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-4-carbon",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-4-carbon",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-4-carbon",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Gemini 4 Carbon FAQ

How much does Gemini 4 Carbon cost?

Gemini 4 Carbon costs $2.3276 / 1M tokens for input and $11.638 / 1M tokens for output on AI/ML API. Cached input is billed at $0.11638 / 1M tokens.

Which reasoning effort should I start with?

Start with medium. Move to high if multi-step answers fall short, or to low for faster responses with fewer reasoning tokens.

What can I send to Gemini 4 Carbon here?

This endpoint is listed with image and text input and text output. Google lists text, image, audio, video and PDF input for the model itself.

How does it differ from Gemini 4 Argon?

Google says Gemini 4 Carbon uses more tokens than Gemini 4 Argon to reason deeply and run extended verification loops. Test both on your own hardest tasks.

How long can a response be?

The maximum output is 65,536 tokens. Reasoning tokens count toward generated output, so hard prompts leave less room for the visible answer.

What is the Gemini 4 Carbon model ID?

Use google/gemini-4-carbon as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of Gemini 4 Carbon?

Gemini 4 Carbon accepts up to 1,048,576 tokens of context and returns up to 65,536 output tokens.

Start building with Gemini 4 Carbon

Get API key

Gemini 4 Carbon API

google/gemini-4-carbon

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemini-4-carbon",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemini-4-carbon",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-4-carbon",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Gemini 4 Carbon API

Gemini 4 Carbon overview

Gemini 4 Carbon by Google

Gemini 4 Carbon specs

Expect long reasoning on hard prompts

Set reasoning effort first

Carbon or Argon

Use cases

Capabilities

Gemini 4 Carbon benchmarks by Artificial Analysis

Intelligence

Speed

Cost per task

Benchmark results

Terminal-Bench 4.0

AA-LCR

Gemini 4 Carbon API pricing

Gemini 4 Carbon vs other models: token prices

How to use the Gemini 4 Carbon API

Build with your agent

1Get your API key

2Make your first request

Gemini 4 Carbon FAQ

Start building with Gemini 4 Carbon

Gemini 4 Carbon API

Build with your agent

1Get your API key

2Make your first request

Gemini 4 Carbon API

Gemini 4 Carbon overview

Gemini 4 Carbon by Google

Gemini 4 Carbon specs

Expect long reasoning on hard prompts

Set reasoning effort first

Carbon or Argon

Use cases

Capabilities

Intelligence

Speed

Cost per task

Benchmark results

Terminal-Bench 4.0

AA-LCR

Gemini 4 Carbon API pricing

Gemini 4 Carbon vs other models: token prices

How to use the Gemini 4 Carbon API

Build with your agent

1Get your API key

2Make your first request

Models similar to Gemini 4 Carbon

Gemini 4 Argon

Gemini 3.8 Flash

Gemini 3.7 Flash

GPT-5.4

Chat GPT audio

Chat GPT 4o audio preview

Gemini 4 Carbon FAQ

Start building with Gemini 4 Carbon