Estimate a Gemini call
Sample
Input: 10,000 tokens Output: 500 tokens
What you get
Adjust model tier to match Google AI Studio or Vertex pricing.
Gemini 3.1 Deep Think Token Calculator
Google's Gemini 3.1 Deep Think models introduce variable-cost thinking tokens. This calculator helps you estimate total API spend including both standard and thinking tokens across Pro, Flash, and Nano tiers.
Gemini 3.1 Deep Think Token Calculator
Model Pricing (per 1M tokens)
| Model | Input | Output | Thinking |
|---|---|---|---|
| Gemini 3.1 Pro | $3.50 | $10.50 | $10.50 |
| Gemini 3.1 Flash | $0.07 | $0.30 | $0.30 |
| Gemini 3.1 Nano | $0.03 | $0.10 | $0.10 |
Per Request
$0.008750
Daily
$0.8750
Monthly
$26.25
Annual
$315.00
How to Use This Tool
- Select the Gemini 3.1 variant (Pro, Flash, or Nano).
- Enter your input and output token estimates.
- Toggle Deep Think mode to include thinking token costs.
- Set your expected request volume.
- View the full cost breakdown with thinking overhead.
Features
- Gemini 3.1 Pro, Flash, and Nano pricing
- Thinking token cost calculation (unique to Deep Think)
- Grounding with Google Search cost add-on
- Context caching discount estimation
- Comparison with OpenAI and Anthropic equivalents
Example
Frequently Asked Questions
What are thinking tokens in Gemini 3.1 Deep Think?
Thinking tokens are intermediate reasoning tokens generated by the model during complex tasks. They are billed at output token rates but are not returned in the response. Deep Think can use 2-10x more thinking tokens than output tokens.
Is Gemini 3.1 Flash cheaper than GPT-5.4 Mini?
Gemini 3.1 Flash is competitively priced with GPT-5.4 Mini. Flash costs approximately $0.075/$0.30 per 1M input/output tokens, making it one of the most cost-effective options for high-volume workloads.
Related Tools
GPT-5.4 Token & API Cost Calculator
Calculate API costs for all GPT-5.4 models with current 2026 pricing.
Claude 4.7 API Cost Estimator
Estimate costs for Claude 4.7 Opus, Sonnet, and Haiku models.
Llama 4 Self-Hosting Cost Estimator
Estimate GPU and cloud costs for self-hosting Llama 4 models.
RAG vs Fine-Tuning Cost Comparison Calculator
Compare RAG and fine-tuning costs to find the optimal approach for your project.
AI Token Counter & API Cost Calculator
Count tokens, words, and characters across all major LLMs and estimate API costs in real time.