Gemini API Cost Calculator

Estimate your Google AI spend across Gemini 3.1 Pro, Gemini 2.5 Pro, Gemini 2.5 Flash-Lite, and Flash Lite. See cost per request, per 1K requests, and monthly totals.

Typical request:
By volume:
Thinking mode uses additional tokens for reasoning

Cost Estimate

Input cost per request $0.0000
Output cost per request $0.0000
Total cost per request $0.0000
Cost per 1,000 requests $0.00
Daily cost $0.00
Monthly cost $0.00
Annual cost $0.00

All Google Gemini Models — Cost Comparison

See how your costs compare across all Gemini models with your current settings

Cheaper Alternatives from Other Providers

These models from other providers offer similar capabilities at lower prices:

Model Provider Input/1M Output/1M Your Cost/Req Savings vs Selected

Unlock the full Gemini cost calculator with Pro

Save scenarios, export reports, get optimization tips. No signup required.

Free Tools → Free Tools →

Google Gemini API Pricing Explained

Google's Gemini API offers some of the most competitive pricing in the AI space. GPT-oss 20B at $0.08/$0.35 is the cheapest AI APIs available — 33x cheaper than GPT-4o for input tokens. Even the premium Gemini 3.1 Pro ($2/$12) undercuts Claude Sonnet 4.6 ($3/$15) on input pricing.

When to Use Each Gemini Model

  • Gemini 3.1 Pro ($2/$12): Latest and most capable. Best for complex reasoning, code generation, and multi-modal tasks. 1M context window.
  • Gemini 2.5 Pro ($1.25/$10): Excellent balance of quality and cost. Great for analysis, summarization, and content generation. 1M context.
  • Gemini 2.5 Flash-Lite ($0.10/$0.40): Budget champion with premium features. Handles most chatbot, classification, and extraction workloads. 1M context.
  • Gemini 2.5 Flash-Lite ($0.075/$0.30): Ultra-budget option. Perfect for high-volume, simple tasks. 1M context window at rock-bottom prices.

How to Reduce Your Gemini API Costs

  • Use Flash for simple tasks: Route classification and extraction to Flash Lite, complex reasoning to Pro. Saves 90%+.
  • Enable prompt caching: Google offers context caching for repeated prefixes — up to 75% discount on cached input tokens.
  • Batch processing: Use the Batch API for non-urgent tasks — 50% discount.
  • Set token limits: Control output length with max_output_tokens to avoid surprise costs.
  • Monitor usage: Set up billing alerts in the Google Cloud console to catch cost spikes early.

Gemini Free Tier

Google offers a generous free tier for Gemini API: Gemini 2.5 Flash-Lite: 15 RPM, 1M tokens/day. Flash Lite: 30 RPM, 1.5M tokens/day. The free tier is great for prototyping and low-traffic applications. For production, paid pricing kicks in once you exceed free limits.

Related Tools

Want to compare Google Gemini with other providers?

Gemini vs ChatGPT → 🔌 Free MCP Server →
This was a snapshot. What about next month?
Prices change. New models launch. Our tools catch what a one-time calculation can't — and saves you money every month.
Free Tools → 🔍 Free audit first

All Tools Are Free

No signup required to 67-model comparison, migration code snippets, PDF reports, price alerts, and cost monitoring. ✅ All tools free.

Free Tools →