Google

Gemini 4 Carbon

The top tier of the Gemini 4 family, built for problems that test the limits of frontier intelligence. Compared with Argon it spends more thinking tokens on hypothesis exploration, root-cause isolation and extended build-and-verify loops, making it a fit for multi-package migrations, architectural redesign and code auditing, formal math, open-ended scientific discovery, and grounded synthesis over dense PDFs, video, charts and tables. It shares Argon's unified 1M-token context, text/image/video/audio/PDF inputs, and low/medium/high thinking levels. The trade-off is more tokens and slower turnaround: Google still recommends Argon for the majority of day-to-day engineering and knowledge work, with Carbon best used for upfront architecture, coordination and final verification while parallel implementation goes to Argon or Flash. Introductory pricing matches Argon ($2/M input, $10/M output through Nov 30, 2026; $4/$20 from Dec 1).

  • Reasoning
  • Web search
  • Tool use
  • Function calling
  • Structured output
  • Long context
  • Code execution

AI Chat

Send a prompt and see the response here.

gemini-4-carbon
Current conversation
How can I help you?

Start a conversation with this model and ask follow-up questions.

Uses your account balance at the model’s current rates.

USD /1M tokens

Pricing

GroupInputOutputCache Read
default$2.1$10.5$0.09996
default
Input$2.1Output$10.5Cache Read$0.09996

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1beta/models/gemini-4-carbon:generateContent' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Hello"
                }
        }
    ]
}'

Google

Related models

GeminiGoogleGemini 3 PRO Image Preview

Built for image generation and editing, with stronger multimodal understanding, conversational edits, and rapid visual prototyping than earlier Gemini image capabilities. Compared with GPT Image, Qwen Image, and Seedream, it is useful for combining documents, images, and prompts in one visual workflow.

$0.0938/imageGeminiGoogleGemini 3.5 Flash Lite

The fastest and most cost-effective model in the Gemini 3.5 line, built for high-throughput, low-latency work such as translation, classification, document processing, and lightweight agentic workflows. It supports multimodal inputs and up to a 1M-token context, while demanding reasoning, long-horizon planning, or high-quality code changes are better handled by a higher-tier Flash model.

$0.3/1M tokensGeminiGoogleGemini 3.1 PRO Preview

Built for multimodal understanding, coding, and long-context tasks, improving over Gemini 3.0 / 2.5 in throughput, context, and tool capabilities. Compared with GPT, Claude, and Qwen models, it is strong for unified analysis workflows across text, images, audio, video, and documents.

$1.4/1M tokensGeminiGoogleGemini 3.1 Flash Image Preview

Built for image generation and editing, with stronger multimodal understanding, conversational edits, and rapid visual prototyping than earlier Gemini image capabilities. Compared with GPT Image, Qwen Image, and Seedream, it is useful for combining documents, images, and prompts in one visual workflow.

$0.028/image

FAQ

Frequently asked questions

What is Gemini 4 Carbon best suited for?

Gemini 4 Carbon is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is Gemini 4 Carbon priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call Gemini 4 Carbon?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with Gemini 4 Carbon

Use in Console