Wirestack
Gemini 4 Carbon is generally available: $2 / $10 until November 30, no temperature or explicit caching (November 10, 2026)
gemini-4-carbon is GA on the paid tier. Prices double Dec 1. Sampling parameters are ignored and explicit caching is not supported.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Google Gemini API API keyGEMINI_API_KEYGet key
Click Create API key
3 of 3 free copies left this month.Unlimited with Pro
What changed
On November 10, 2026 Google made Gemini 4 Carbon (gemini-4-carbon) generally available in the Gemini API. Google calls it its most capable reasoning model, built for long agentic coding and multimodal knowledge work.
- Paid tier only. It is not on the Free tier.
- Price, per 1M tokens: $2.00 input, $10.00 output (thinking tokens count as output), $0.10 cached input, through November 30, 2026. From December 1, 2026 it is $4.00 input, $20.00 output, $0.20 cached input. Batch is half those rates.
- Context: 1,048,576 tokens shared by input, thinking and output. A normal response stops at 65,536 tokens; with
background=Trueand a highermax_output_tokensit can run longer. - Thinking:
thinking_levelislow,medium(the default) orhigh.max_output_tokenscaps thinking plus output together.
What can break when you switch from Gemini 3 or earlier:
temperature,top_pandtop_kare ignored. Remove them.- Explicit caching is not supported (
caches.create,cached_content). Remove those calls. Implicit caching is on by default for prompts of 4,096 tokens or more. - Hard prompts can take several minutes. Google recommends background mode or HTTP timeouts of at least 15 minutes.
Prerequisites
- A Gemini API key in
GEMINI_API_KEY, from a project on a paid tier - The Google Gen AI SDK (
google-genaifor Python)
Steps
- Change the model ID to
gemini-4-carbon. Coming from , that is the only change to the request.