Estimate a Gemini 3.8 Flash call
Sample
Input: 10,000 tokens Output: 500 tokens
What you get
Adjust model tier to match Google AI Studio or Vertex pricing (Gemini 3.8 Flash and nearby tiers).
Gemini Token & API Cost Calculator
Google’s Gemini lineup changes quickly. This calculator loads active Gemini models — including Gemini 3.8 Flash and nearby Flash/Pro tiers — and rates from OpenRouter, and can estimate thinking/reasoning tokens when a model is marked for reasoning. Live model lists and $/1M rates load from OpenRouter’s public models API (https://openrouter.ai/api/v1/models), with TensorFeed and a local snapshot as fallbacks. New releases (for example Gemini 3.8 Flash or Claude Fable 5.1) appear automatically when OpenRouter lists them.
Gemini Token & API Cost Calculator
Google · Local registry · as of 2026-09-02 · 5 models · refreshing…
Pricing data: OpenRouter models
Model Pricing (per 1M tokens)
| Model | Input | Output | Thinking |
|---|---|---|---|
| Gemini 3.8 Flash | $0.75 | $3.75 | $3.75 |
| Gemini 3.7 Flash | $0.75 | $3.75 | $3.75 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $9.00 |
| Gemini 3.1 Pro | $2.00 | $12.00 | $12.00 |
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | $1.50 |
Per Request
$0.002625
Daily
$0.2625
Monthly
$7.87
Annual
$94.50
How to Use This Tool
- Select the Gemini variant you plan to call (e.g. 3.8 Flash).
- Enter your input and output token estimates.
- If available, toggle thinking/reasoning tokens for a fuller cost picture.
- Set your expected request volume.
- View the full cost breakdown.
Features
- Live Google Gemini models via OpenRouter (incl. 3.8 Flash)
- Optional thinking/reasoning token estimate
- Per-request through annual projections
- Side-by-side pricing table
- Ready for new Gemini versions without UI rewrites
Example
Frequently Asked Questions
What are thinking tokens?
Some Gemini models bill intermediate reasoning tokens. When a model is flagged for reasoning, we can estimate thinking cost as a multiple of output tokens. Confirm exact billing in Google’s pricing docs.
Do long-context tiers change the price?
Yes. Google often charges more above ~200K input tokens. Figures here are the published list prices OpenRouter surfaces for planning.
How do new Gemini models get added?
They appear when OpenRouter’s Google provider list updates. This tool filters that live catalog to Google models.
Related Tools
GPT Token & API Cost Calculator
Calculate API costs for current OpenAI GPT models with live OpenRouter pricing.
Claude API Cost Estimator
Estimate costs for Claude Fable 5.1 and other current Anthropic models with live pricing.
AI Token Counter & API Cost Calculator
Count tokens and estimate API costs across major LLMs — models update from OpenRouter live pricing.
Llama Self-Hosting Cost Estimator
Estimate GPU and cloud costs for self-hosting Llama models.
RAG vs Fine-Tuning Cost Comparison Calculator
Compare RAG and fine-tuning costs to find the optimal approach for your project.