Google · Very Fast · Updated 2026-11

Gemini 2.5 Flash API Pricing & Cost Breakdown

High-throughput agents, 1M-context RAG, multimodal pipelines, and cost-sensitive SaaS.

Input / 1M Tokens
$0.15
Cached Input / 1M
$0.037
Output / 1M Tokens
$0.60
Context Window
1M

Workload Cost Scenarios (30-Day Billing)

Non-thinking output rate shown ($0.60/1M); thinking mode increases output pricing ($3.50/1M).

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $1.40 $1.14
Growing Startup (2,500 req/day) 2500 / 700 $59.63 $49.08
Production Scale (50,000 req/day) 3000 / 800 $1,395.00 $1,141.88

Compare Gemini 2.5 Flash Against Alternatives

Lower-Cost Alternative Models

Gemini 2.0 Flash ($0.40/1M out) Qwen 2.5 72B ($0.40/1M out) Grok 3 Mini ($0.50/1M out)

Frequently Asked Questions

What is Gemini 2.5 Flash API pricing per 1M tokens?

Standard input is $0.15/1M, cached input is $0.037/1M, and output is $0.60/1M.

What is the context window of Gemini 2.5 Flash?

Gemini 2.5 Flash supports a 1M token context window with up to 65,536 max output tokens.

How much does prompt caching save on Gemini 2.5 Flash?

Prompt caching reduces cached input token rates by 75% compared with uncached input.

What workloads is Gemini 2.5 Flash best suited for?

High-throughput agents, 1M-context RAG, multimodal pipelines, and cost-sensitive SaaS.