Google Gemini 4 Carbon: Pricing, Specs and Limits
Google Gemini 4 Carbon: frontier Gemini 4 model for coding, agentic and complex reasoning work, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs...
By ShilpBot Team · Published · 3 min read
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 and supports long outputs.
It sits next to Argon at the same price, so the real choice is which one suits your task. Google describes Argon as its flagship reasoning model, while Carbon is aimed at coding and agentic work.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Google Gemini 4 Carbon quick facts
| Detail | Value |
|---|---|
| Developer | |
| Model ID | google/gemini-4-carbon |
| Added to the catalogue | 2026-11-10 |
| Type | Frontier Gemini 4 model for coding, agentic and complex reasoning work |
| Parameters | Not listed |
| Context window | about 1M tokens (1,048,576) |
| Maximum output | 943,718 tokens |
| Input types | audio, file, image, text, video |
| Price | 2.00 in / 10.00 out per 1M tokens (cached input 0.10) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Google Gemini 4 Carbon is good for
- Coding and agent tasks that need large context and multimodal input.
- Long-document analysis up to about 1M tokens.
- Teams that want one model for text, audio, images, video and files.
Limits of Google Gemini 4 Carbon
- At $10 per million output tokens, runaway agent loops get expensive. Set step and token limits.
- Same price as Argon, so compare both on your workload before committing.
- Long contexts raise input cost. Use cached input where your client supports it.
How Google Gemini 4 Carbon compares
- Google Gemini 4 Argon: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 2.00 input and 10.00 output per million tokens against 2.00 and 10.00.
- Google Gemini 4 Hydrogen: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 2.00 input and 10.00 output per million tokens against 1.50 and 7.50.
- Anthropic Claude Sonnet 5.5: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 943,718 tokens against 128,000; it also accepts audio and video input; it costs 2.00 input and 10.00 output per million tokens against 2.00 and 10.00.
Calling Google Gemini 4 Carbon from code
Use the model ID google/gemini-4-carbon with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemini-4-carbon", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Google Gemini 4 Carbon can do
- Give it a medium-sized repository summary and ask for a refactoring plan with risks.
- Send a screen recording of a bug and ask for reproduction steps.
- Run the same task on Carbon and Argon and compare quality, tokens used and cost.
What Google Gemini 4 Carbon costs
The catalogue lists 2.00 per million input tokens and 10.00 per million output tokens, with cached input at 0.10 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 3.00. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.40 before caching. If your client reuses the same prompt prefix, cached input at 0.10 per million tokens can cut the input side of that bill by about 95 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
Is Gemini 4 Carbon cheaper with caching?
The catalogue lists cached input at $0.10 per million tokens against $2.00 for uncached input, so repeated large prompts cost far less when caching applies.
What are the cost and limits of Google Gemini 4 Carbon?
As of 2026-11-16 the catalogue lists 2.00 per million input tokens and 10.00 per million output tokens. About 1M tokens (1,048,576) context window, up to 943,718 output tokens, model ID google/gemini-4-carbon. Prices can change, so check the live model page.
