Input
$2
Output
$10
Context
1M
Gemini 4 Carbon costs $2 per million input tokens and $10 per million output tokens. Cached input is billed at $0.10 per million, 95% less than fresh input.
Specifications
| Lab | |
| Model id | google/gemini-4-carbon |
| Input price | $2 per million tokens |
| Output price | $10 per million tokens |
| Cached input price | $0.10 per million tokens |
| Context window | 1,048,576 tokens (1M) |
| Maximum output | 943,718 tokens (944K) |
| Tool calling | yes |
| Image input | yes |
| Reasoning | yes |
| Intelligence index | 60 |
| First listed | 10 November 2026 |
Models it replaced
The feeds list Gemini 4 Carbon in place of google/gemini-2.5-pro, google/gemini-2.5-pro-preview, google/gemini-3.1-pro-preview. Those models' own prices and limits were different; an article that names one of them describes the model it was written about.
Google's other models
| Model | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Gemini Omni 1.2 Flash | $1.50 | $9 | 128K | 5 November 2026 |
| Gemini Omni 1.1 Flash | $1.50 | $9 | 128K | 4 November 2026 |
| Gemini 4 Argon | $2 | $10 | 1M | 13 October 2026 |
| Nano Banana 2.1 | $1.50 | $7.50 | 64K | 6 October 2026 |
| Gemini 3.8 Flash | $0.75 | $3.75 | 1M | 2 September 2026 |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | 1M | 21 July 2026 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $0.25 | $1.50 | 64K | 30 June 2026 |
| Nano Banana Pro (Gemini 3 Pro Image) | $2 | $12 | 128K | 18 June 2026 |
| Nano Banana 2 (Gemini 3.1 Flash Image) | $0.50 | $3 | 128K | 18 June 2026 |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | 1M | 7 May 2026 |
| Gemma 4 26B A4B | $0.08 | $0.10 | 256K | 3 April 2026 |
| Gemma 4 31B | $0.20 | $0.40 | 256K | 2 April 2026 |
Where these numbers come from
Read from OpenRouter's listing of Gemini 4 Carbon every 6 hours, with Google's own /models endpoint confirming the model, into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.