LLM Cost Calculator

Google Gemini API Pricing 2026

Gemini 3.6 Flash is Google's latest stable model for agentic and multimodal tasks. Gemini 3.5 Flash-Lite targets high-throughput workloads, and both support a 1M-token context window.

Pricing verified 2026-08-03. Sourced from ai.google.dev/gemini-api/docs/pricing.

Get Google Gemini API access →

Google Gemini Model Pricing

Prices in USD per 1M tokens

ModelInput / 1MOutput / 1MContext
Gemini 3.5 Flash Lite
Fastest low-cost Gemini 3.5 model for high-throughput tasks; 1M context
$0.3$2.51,048,576
Gemini 3.6 Flash
Latest stable Gemini Flash; agentic and multimodal workloads; 1M context
$1.5$7.51,048,576
Gemini 3.5 Flash
Latest Gemini; frontier intelligence + superior search & grounding
$1.5$91,000,000
Gemini 3.1 Flash-Lite
Most cost-efficient Gemini; high-volume agentic tasks
$0.25$1.51,000,000
Gemini 3.1 Pro Preview
Advanced multimodal + agentic capabilities
$2$121,000,000
Gemma 4 26B A4B
Gemma 4 MoE 26B (4B active); fast open-weights model
$0.07$0.34262,144
Gemma 4 31B
Gemma 4 dense 31B; top open-weights model from Google
$0.1$0.34262,144
Gemini 2.5 Flash
Hybrid reasoning; 1M context with thinking budgets
$0.3$2.51,000,000
Gemini 2.5 Flash-Lite
Smallest & cheapest Gemini 2.5; built for scale
$0.1$0.41,000,000
Gemini 2.5 Pro
Stable release; strong coding & complex reasoning
$1.25$101,000,000

How to read these estimates

The monthly table assumes 70% input tokens and 30% output tokens. It is a consistent comparison baseline, not a prediction of your workload. Actual bills can also include cached-input discounts, batch pricing, tool calls, minimum charges, regional differences, retries, and taxes.

The linked source is the provider's pricing documentation. Verify the current rate card and model availability before committing to a budget.

Estimated Monthly Cost (70% input / 30% output split)

Model1M tokens/mo10M tokens/mo100M tokens/mo1B tokens/mo
Gemini 3.5 Flash Lite$0.960$9.60$96.00$960
Gemini 3.6 Flash$3.30$33.00$330$3,300
Gemini 3.5 Flash$3.75$37.50$375$3,750
Gemini 3.1 Flash-Lite$0.625$6.25$62.50$625
Gemini 3.1 Pro Preview$5.00$50.00$500$5,000
Gemma 4 26B A4B $0.151$1.51$15.10$151
Gemma 4 31B$0.172$1.72$17.20$172
Gemini 2.5 Flash$0.960$9.60$96.00$960
Gemini 2.5 Flash-Lite$0.190$1.90$19.00$190
Gemini 2.5 Pro$3.88$38.75$388$3,875

Frequently Asked Questions

How much does Google Gemini LLM API cost?

Google Gemini offers 10 models ranging from $0.070/1M to $2.00/1M input tokens. Gemini 3.6 Flash is Google's latest stable model for agentic and multimodal tasks. Gemini 3.5 Flash-Lite targets high-throughput workloads, and both support a 1M-token context window.

Is Google Gemini cheaper than self-hosting?

For low-volume workloads (under 100M tokens/month), cloud APIs like Google Gemini are almost always cheaper than purchasing and maintaining GPU hardware. Use our calculator to find the exact break-even point for your usage.