Gemini 4 Carbon API pricing
Gemini 4 Carbon costs $2 per million input tokens and $10 per million output tokens on Google's API. Input read back from the prompt cache costs $0.10 per million. A typical support chat reply (1,500 tokens in, 300 out) costs about $0.0060.
| Input | $2 per 1M tokens |
|---|---|
| Output | $10 per 1M tokens |
| Cached input | $0.10 per 1M tokens |
| Context window | 1.05M tokens |
| Reads | audio, files, images, text, video |
| Released | November 10, 2026 |
Gemini 4 Carbon. Input: $2.00 per 1M tokens through November 30, 2026, then $4.00 from December 1, 2026.
Gemini 4 Carbon. Output: $10.00 per 1M tokens through November 30, 2026, then $20.00 from December 1, 2026.
What requests cost on Gemini 4 Carbon
The same four requests on every page, so you can compare models directly.
| Request | Tokens in / out | Per request | Per 10,000 requests |
|---|---|---|---|
| A support chat reply | 1,500 / 300 | $0.0060 | $60.00 |
| Summarizing a 10-page document | 6,000 / 500 | $0.017 | $170 |
| Sorting a support ticket into a category | 400 / 5 | $0.00085 | $8.50 |
| A question about a 120-page document | 60,000 / 800 | $0.128 | $1,280 |
Google's cheapest model here, Gemini 2.5 Flash-Lite, costs 96% less for the same chat reply. Whether it is good enough depends on the request: simple ones (sorting, short summaries, extraction) often are, hard reasoning often isn't.
Other Google models
| Model | Input | Output | A chat reply | Next to Gemini 4 Carbon |
|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $0.00027 | 96% less |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.00082 | 86% less |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | $0.0012 | 80% less |
| Gemini 2.5 Flash | $0.30 | $2.50 | $0.0012 | 80% less |
| Gemini 3 Flash Preview | $0.50 | $3 | $0.0016 | 73% less |
| Gemini 3.8 Flash | $0.75 | $3.75 | $0.0022 | 63% less |
| Gemini 3.6 Flash | $0.75 | $3.75 | $0.0022 | 63% less |
| Gemini 4 Hydrogen | $1.50 | $7.50 | $0.0045 | 25% less |
| Gemini 2.5 Pro | $1.25 | $10 | $0.0049 | 19% less |
| Gemini 4 Argon | $2 | $10 | $0.0060 | same price |
| Gemini 3.1 Pro Preview | $2 | $12 | $0.0066 | 10% more |
Similar price from other companies
| Model | Input | Output | A chat reply | Next to Gemini 4 Carbon |
|---|---|---|---|---|
| GPT-6.1 Sol | $2 | $10 | $0.0060 | same price |
| GPT-6 Sol | $2 | $10 | $0.0060 | same price |
| Claude Sonnet 5.5 | $2 | $10 | $0.0060 | same price |
| Claude Sonnet 5 | $2 | $10 | $0.0060 | same price |
| GPT-5.6 Terra | $2 | $12 | $0.0066 | 10% more |
Gemini 4 Carbon pricing questions
How much does the Gemini 4 Carbon API cost per million tokens?
Gemini 4 Carbon costs $2 per million input tokens and $10 per million output tokens on Google's API, and input read back from the prompt cache costs $0.10 per million.
How much do 1,000 tokens cost on Gemini 4 Carbon?
1,000 input tokens cost $0.002 and 1,000 output tokens cost $0.01, at $2 and $10 per million.
What does one request cost on Gemini 4 Carbon?
A typical support chat reply, 1,500 tokens in and 300 out, costs about $0.0060: 1,500 × $2 / 1,000,000 plus 300 × $10 / 1,000,000.
Is there a cheaper Google model than Gemini 4 Carbon?
Yes. Gemini 2.5 Flash-Lite costs $0.10 per million input tokens and $0.40 per million output tokens, so the same chat reply costs about $0.00027. Whether it answers as well depends on the request: test it on your own prompts.
Paying Gemini 4 Carbon prices for every request?
Most apps send simple requests to the same strong model as the hard ones. PromptUnit checks each request your app sends and uses a cheaper model only when it is just as good for that request. You pay 20% of what it saves, and nothing if it saves nothing.
Checked November 13, 2026. Prices are read every day from Google's pricing page. Context window, inputs and release date come from OpenRouter's public model list.
These are the standard list prices on each provider's own API. Batch, flex and priority tiers, cloud platforms such as Amazon Bedrock or Google Vertex AI, and regional endpoints are priced differently. Request costs above count input and output tokens only, not cache, search or image fees.
Free to reuse (CC BY 4.0): today's list as JSON, and a copy of every day on GitHub.