Verified November 2026

Home › Models › Gemini 4 Carbon

Gemini 4 Carbon API pricing

Gemini 4 Carbon is a flagship model from Google Gemini with a 1,000,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026, and include a promotional rate running until Nov 30, 2026.

$2Input / 1M tokens
$10Output / 1M tokens
$0.10Cached input / 1M
1,000,000Context window

Price list

Gemini 4 Carbon rates in USD per 1M tokens, November 2026
Token classRate / 1MNotes
Input$2Prompt tokens not served from cache
Cached input$0.1095% below base input
Cache write—Not billed per token
Output$105.0× the input rate
Batch API−50%Input and output, results within 24 h

Google’s most capable reasoning model. Launch price through Nov 30, 2026; doubles to $4/$20 on Dec 1. Implicit caching only.

What Gemini 4 Carbon costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$14
RAG with caching1,00050K in (45K cached) / 1K out$24.59
Nightly batch job10,00010K in / 2K out$200

Caching the 45K-token prefix saves about 78% on the RAG workload versus sending it uncached every call ($110 → $24.59). Batch mode halves the nightly job.

Where Gemini 4 Carbon sits in the market

Out of 45 models in this dataset, Gemini 4 Carbon ranks #32 cheapest by input rate, #31 by output rate, and #32 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
Gemini 4 CarbonGoogle Gemini$2$10$4.50
Claude Sonnet 5.5Anthropic$2$10$4.50
Gemini 4 ArgonGoogle Gemini$2$10$4.50
Claude Sonnet 5Anthropic$2$10$4.50

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does Gemini 4 Carbon cost per 1M tokens?

$2 per 1M input tokens and $10 per 1M output tokens on the standard tier.

Is prompt caching cheaper on Gemini 4 Carbon?

Yes. Cached input bills at $0.10 per 1M tokens, 95.0% below the $2 base input rate, with no separate cache-write rate published.

Does Gemini 4 Carbon support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $400 at list price and about $200 in batch mode.

Keep reading

Run these numbers in the calculator