Google Gemini 1.5 Pro & Flash API Cost Estimator

GEMINI MODEL & TOKEN USAGE

Select Google Gemini Model

Monthly API Requests

Input Tokens / Req

Output Tokens / Req

Enable Context Caching (75% discount on cached inputs)

GOOGLE GEMINI API COST ESTIMATE

$19.69

Est. Monthly Cost

$0.00020

Cost / Request

300M

Total Tokens/Mo

Cost Distribution

Input Tokens Cost (250M): $4.69 / mo

Output Tokens Cost (50M): $15.00 / mo

Annual Equivalent API Spend: $236.25 / yr

Google Gemini API Pricing & Context Window Optimization

Google Gemini 1.5 Flash and Pro provide high-throughput processing with large context windows (up to 2,000,000 tokens). Flash models deliver cost performance for high-volume API applications.

Google Gemini Pricing Rates (per 1,000,000 Tokens)

Gemini 1.5 Flash: $0.075 Input / $0.01875 Cached Input / $0.30 Output
Gemini 2.0 Flash: $0.10 Input / $0.025 Cached Input / $0.40 Output
Gemini 1.5 Pro (<128k): $1.25 Input / $0.3125 Cached Input / $5.00 Output
Gemini 1.5 Pro (>128k): $2.50 Input / $0.625 Cached Input / $10.00 Output

Related AI Developer Tools

Calculate Anthropic Claude pricing with the Claude Cost Estimator, calculate OpenAI costs with the OpenAI Cost Estimator, or compare all providers using the OpenAI Cost Estimator.

Frequently Asked Questions

Common questions about this tool.

What are the current pricing rates for Google Gemini 1.5 Flash? ▼

Gemini 1.5 Flash costs $0.075 per 1M input tokens ($0.01875 per 1M cached input) and $0.30 per 1M output tokens for prompts under 128k tokens.

How does Gemini 1.5 Pro pricing scale for prompts over 128k tokens? ▼

For prompts <=128k tokens, Gemini 1.5 Pro costs $1.25 per 1M input / $5.00 per 1M output. For prompts >128k tokens up to 2M, input pricing increases to $2.50 per 1M and output to $10.00 per 1M.

How does Google Context Caching reduce API costs? ▼

Google Context Caching allows developers to store large documents or codebases in memory, reducing input token pricing by 75% for cached requests.

What is the maximum context window supported by Gemini 1.5 Pro? ▼

Gemini 1.5 Pro supports an industry-leading 2,000,000 token context window, allowing developers to process full codebases, hours of audio, or long PDF documents.

Is there a free tier available for Google Gemini API? ▼

Yes! Google AI Studio provides a free tier with rate limits (15 RPM for Gemini 1.5 Flash, 2 RPM for Gemini 1.5 Pro) for non-commercial prototyping.