Gemini API Pricing Calculator
Calculate costs for Gemini 2.0 Flash, 1.5 Pro, and multimodal inputs
Select Gemini Model
Usage Configuration
Multimodal Inputs
Add images, video, or PDFs to calculate multimodal costs
Model Comparison
| Model | Context | Per Request | Monthly Cost | vs Selected |
|---|---|---|---|---|
Gemini 2.0 FlashSelected | 1M | $0.000300 | $0.90 | - |
Gemini 2.0 Flash Thinking | 1M | $0.000300 | $0.90 | -$0.00 |
Gemini 1.5 Flash | 1M | $0.000225 | $0.67 | -$0.23 |
Gemini 1.5 Pro | 2M | $0.003750 | $11.25 | +$10.35 |
Gemini 1.0 Pro | 32K | $0.001250 | $3.75 | +$2.85 |
About Google Gemini Models:
- Gemini 2.0 Flash is the latest model with native tool use and real-time capabilities
- All Gemini models support multimodal inputs (text, images, video, audio, PDFs)
- Flash models offer the best cost/performance ratio for most applications
- 1.5 Pro offers 2M token context - largest in the industry
- Significantly cheaper than GPT-4o for equivalent capabilities
- Prices current as of January 2025 - check Google AI for latest
How to Use the Gemini API Pricing Calculator
Select a Gemini Model
Choose from Gemini 2.0 Flash (fastest, cheapest), Gemini 1.5 Pro (highest quality, 2M context), or Gemini 1.5 Flash (previous gen). Each offers different capabilities and price points.
Enter Text Token Usage
Input your expected input and output tokens for text processing. Gemini offers some of the lowest text pricing in the industry, especially with 2.0 Flash at just $0.10 per million input tokens.
Add Multimodal Inputs (Optional)
If processing images, video, or PDFs, enter the quantity. Images cost about 258 tokens each, video is ~300 tokens per second, and PDFs average ~500 tokens per page.
Calculate Total Cost
View your total estimated cost including text and multimodal components. Compare with GPT-4o pricing to see potential savings of up to 25x on similar workloads.
Pro tip: Your data is processed entirely in your browser. Nothing is sent to any server, ensuring complete privacy.
Understanding Gemini API Pricing
Google's Gemini API offers some of the most competitive pricing in the AI industry, with the 2.0 Flash model being particularly cost-effective. Understanding the pricing structure, especially for multimodal inputs, helps you budget accurately for your AI applications.
Gemini Model Comparison
Gemini 2.0 Flash ($0.10/$0.40 per 1M tokens) is the latest and most cost-effective model, offering native tool use, real-time capabilities, and excellent multimodal performance at a fraction of competitor prices.
Gemini 1.5 Pro ($1.25/$5.00 per 1M tokens) offers the highest quality and an industry-leading 2 million token context window. Best for tasks requiring extensive context or premium output quality.
Gemini 1.5 Flash ($0.075/$0.30 per 1M tokens) is the previous generation's fast model, still offering excellent performance at slightly lower prices than 2.0 Flash.
Multimodal Pricing Explained
All Gemini models support multimodal inputs - images, video, audio, and PDFs. These are converted to tokens for pricing:
- Images: ~258 tokens per image (varies by size)
- Video: ~300 tokens per second (1 hour = 1.08M tokens)
- Audio: ~40 tokens per second
- PDFs: ~500 tokens per page
Gemini vs GPT-4o Pricing
Gemini offers significant cost savings compared to OpenAI's GPT-4o. For the same workload, Gemini 2.0 Flash is approximately 25x cheaper for input tokens and 25x cheaper for output tokens. This makes Gemini an attractive choice for cost-sensitive applications without sacrificing capability.
Frequently Asked Questions
How much does Gemini 2.0 Flash cost?
Gemini 2.0 Flash costs $0.10 per million input tokens and $0.40 per million output tokens. This makes it one of the most cost-effective frontier AI models available, significantly cheaper than GPT-4o.
What is the difference between Gemini Flash and Pro?
Gemini Flash models are optimized for speed and cost-efficiency, while Pro models offer higher quality for complex tasks. Flash is 10-15x cheaper but Pro has a 2M token context window (vs 1M for Flash) and better performance on nuanced tasks.
Is Gemini cheaper than GPT-4?
Yes, Gemini is significantly cheaper than GPT-4o. Gemini 2.0 Flash costs $0.10/$0.40 per million tokens compared to GPT-4o's $2.50/$10.00 - making Gemini about 25x cheaper for the same token usage.
How are multimodal inputs priced in Gemini?
Multimodal inputs are converted to tokens for pricing. Images are approximately 258 tokens each, video is about 300 tokens per second, and PDFs are roughly 500 tokens per page. These tokens are charged at the input token rate.
Related Tools
Compare AI API costs across OpenAI GPT-4, Anthropic Claude, Google Gemini, and more. Calculate monthly costs based on your token usage. Updated 2025 pricing.
Count tokens for OpenAI GPT-4, Claude 3, Gemini, and other LLMs. See token breakdown by model, estimate API costs instantly. Supports cl100k_base and other tokenizers.
Calculate Anthropic Claude API costs. Compare Claude 3 Opus, Sonnet, and Haiku pricing.
Calculate DeepSeek API costs and compare with other providers.