Google · Fast · Updated 2026-11-22

Gemini 4 Carbon API Pricing & Cost Breakdown

Long-context multimodal agents, document/video analysis, and coding pipelines.

Input / 1M Tokens
$2.00
Cached Input / 1M
$0.100
Output / 1M Tokens
$10.00
Context Window
1.05M

Workload Cost Scenarios (30-Day Billing)

Matches GPT-6.2 Sol & Claude Sonnet 5.5 at $2.00/$10.00 per 1M tokens.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $21.00 $16.73
Growing Startup (2,500 req/day) 2500 / 700 $900.00 $721.88
Production Scale (50,000 req/day) 3000 / 800 $21,000.00 $16,725.00

Compare Gemini 4 Carbon Against Alternatives

Lower-Cost Alternative Models

GPT-6 Luna ($0.50/1M out) Claude Haiku 5.5 ($0.50/1M out) DeepSeek V4.1 Flash ($0.60/1M out) Llama 4 Maverick ($1.00/1M out)

Frequently Asked Questions

What is Gemini 4 Carbon API pricing per 1M tokens?

Standard input is $2.00/1M, cached input is $0.100/1M, and output is $10.00/1M.

What is the context window of Gemini 4 Carbon?

Gemini 4 Carbon supports a 1.05M token context window with up to 943,718 max output tokens.

How much does prompt caching save on Gemini 4 Carbon?

Prompt caching reduces cached input token rates by 95% compared with uncached input.

What workloads is Gemini 4 Carbon best suited for?

Long-context multimodal agents, document/video analysis, and coding pipelines.