Google Gemini API Cost Calculator
Calculate costs for all Gemini models including Gemini 3.1 Pro Preview, Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, and more
Token Cost Calculator
Enter your estimated token usage to calculate costs
Latest Pro model with improved reasoning and 1M token context
≈ 750 words
≈ 7500 words
Real-time Calculation
Instant cost estimates for your API usage
All Models Supported
From Flash to Pro models
Advanced Features
Long context and caching support
Current Gemini API Pricing
Latest Google Gemini model prices per million tokens
Gemini 3.1 Pro Preview
Input: $2.00/1M (≤200k), $4.00/1M (>200k)
Output: $12.00/1M (≤200k), $18.00/1M (>200k)
Cache: $0.20/1M (≤200k), $0.400/1M (>200k)
Gemini 3 Pro Preview
Input: $2.00/1M (≤200k), $4.00/1M (>200k)
Output: $12.00/1M (≤200k), $18.00/1M (>200k)
Cache: $0.20/1M (≤200k), $0.400/1M (>200k)
Gemini 3 Flash Preview
Input: $0.500/1M tokens (text)
Audio Input: $1.000/1M tokens
Output: $3.000/1M tokens
Free tier available (1000 queries/day)
Gemini 2.5 Pro
Input: $1.25/1M (≤200k), $2.50/1M (>200k)
Output: $10.00/1M (≤200k), $15.00/1M (>200k)
Cache: $0.13/1M (≤200k), $0.250/1M (>200k)
Free tier available (1000 queries/day)
Gemini 2.5 Flash
Input: $0.300/1M tokens (text)
Audio Input: $1.000/1M tokens
Output: $2.500/1M tokens
Free tier available (1000 queries/day)
Gemini 2.5 Flash-Lite
Input: $0.100/1M tokens (text)
Audio Input: $0.300/1M tokens
Output: $0.400/1M tokens
Free tier available (1000 queries/day)
Gemini 2.0 Flash
Input: $0.100/1M tokens (text)
Audio Input: $0.700/1M tokens
Output: $0.400/1M tokens
Free tier available (1000 queries/day)
Gemini 2.0 Flash-Lite
Input: $0.075/1M tokens (text)
Output: $0.300/1M tokens
Free tier available (1000 queries/day)
Gemini API Price Calculator: Token Cost Estimation Tool
Our comprehensive Gemini token calculator helps you estimate costs for all Google Gemini models. Whether you're using Gemini 3.1 Pro Preview for the latest reasoning capabilities, Gemini 3 Pro Preview for frontier multimodal reasoning, Gemini 3 Flash Preview for fast next-gen performance, Gemini 2.5 Pro for coding and complex tasks, or Gemini 2.5 Flash-Lite for budget-friendly workloads, calculate your API costs instantly.
Latest Models
- • Gemini 3.1 Pro Preview: Latest Pro with improved reasoning
- • Gemini 3 Pro Preview: Multimodal understanding with tiered pricing
- • Gemini 3 Flash Preview: Fast next-gen model with audio support
- • Gemini 2.5 Pro: Excels at coding and complex reasoning
- • Gemini 2.5 Flash: First hybrid reasoning model
- • Gemini 2.5 Flash-Lite: Most cost-effective option
Key Features
- • Token cost calculation for text and audio
- • Tiered pricing for long contexts (>200k tokens)
- • Context caching cost estimation
- • 50% batch API discount available
- • Free tier on most models
How It Works
Calculate your Gemini API costs in three simple steps:
Select Model
Choose from Gemini 3.1 Pro, 3 Pro, 3 Flash, 2.5 Pro, 2.5 Flash, and more
Configure Options
Set input type and context preferences
Enter Tokens
Specify input and output token amounts
Pro Tips
- • Enable context caching for up to 90% savings on repeated inputs
- • Use Batch API for 50% off on non-time-sensitive workloads
- • Keep prompts under 200k tokens to avoid higher tiered rates
- • Free tier available on most models (up to 1,000 requests/day)
Model Comparison & Use Cases
Compare Google Gemini models to find the perfect balance of features and cost.
| Model | Best For | Features | Price Range |
|---|---|---|---|
| Gemini 3.1 Pro Preview | Latest reasoning & multimodal | 1M context, tiered pricing, best quality | $2.00–$4.00 / $12.00–$18.00 |
| Gemini 3 Pro Preview | Previous Pro, multimodal reasoning | 1M context, tiered pricing | $2.00–$4.00 / $12.00–$18.00 |
| Gemini 3 Flash Preview | Fast next-gen tasks | Audio support, free tier, caching | $0.50 / $3.00 |
| Gemini 2.5 Pro | Coding & complex reasoning | Tiered pricing, long context, batch API | $1.25–$2.50 / $10.00–$15.00 |
| Gemini 2.5 Flash | General use, hybrid reasoning | 1M context, audio support, free tier | $0.30 / $2.50 |
| Gemini 2.5 Flash-Lite | Budget-friendly, simple tasks | Lowest cost, audio support, free tier | $0.10 / $0.40 |
| Gemini 2.0 Flash | Stable production workloads | 1M context, audio, caching | $0.10 / $0.40 |
| Gemini 2.0 Flash-Lite | Simple classification & routing | Lowest price point, batch support | $0.075 / $0.30 |
Cost Optimization Tips
Maximize your Gemini API usage while minimizing costs:
Input Optimization
- • Use context caching to save up to 90% on repeated prompts
- • Use Batch API for 50% discount on non-urgent workloads
- • Keep prompts under 200k tokens for lower tiered pricing
- • Optimize prompt length to reduce token usage
Model Selection
- • Start with Gemini 2.5 Flash-Lite ($0.10/1M input)
- • Use Gemini 2.0 Flash-Lite ($0.075/1M) for routing tasks
- • Utilize free tier on most models
- • Escalate to Pro models only for complex tasks
Pricing Updates & Information
Stay informed about Google Gemini API pricing and model updates.
Gemini API prices are subject to change. While we maintain current rates for all models in our calculator, always verify the latest pricing on Google's official website.
Related Calculators
OpenRouter
Compare pricing across all OpenRouter models in one table
OpenAI GPT
Calculate costs for GPT-5.4 pro, GPT-5.4, o3-pro, o3, o4-mini, GPT-4.1 & GPT-4o
Claude
Calculate costs for Claude Opus 4.6, Sonnet 4.5 & Haiku 4.5
DALL-E & GPT Image
Calculate costs for GPT Image 1.5, GPT Image 1, DALL-E 3 & 2
Whisper & TTS
GPT-4o Transcribe, Whisper, TTS & TTS HD pricing
Cohere
Calculate costs for Command A, R+, R & R7B models