Compare inference costs across GPT-5, Claude 4.5, Gemini 3, and more.
Now with agentic loops, caching, and reasoning tokens
In 2026, most AI applications use multi-step "agentic loops" rather than single prompts. Calculate costs for workflows like: "5 research steps + 1 summary step = 6 total steps."
Modern APIs (Anthropic, Gemini, OpenAI) offer context caching that reduces input costs by up to 90% for repeated data. Set your cache hit rate to see potential savings.
Reasoning models (like OpenAI's o-series) "think" before responding. These "thinking tokens" cost extra money and are often missed by older calculators. Enable reasoning to see the true cost.
Enable context caching to save up to 90% on repeated inputs
| Model | Input Price | Output Price | Context | Total Cost | vs. Lowest |
|---|---|---|---|---|---|
Gemini 3 ProGoogle | $1.25/1M | $10.00/1M | 2.0M | $0.0825 | Lowest |
Copy-paste code to integrate Gemini 3 Pro into your application
import google.generativeai as genai
genai.configure(api_key="your-api-key")
model = genai.GenerativeModel('gemini-3-pro')
response = model.generate_content(
"Your prompt here",
generation_config={
"max_output_tokens": 2000
}
)
print(response.text)💡 Replace "your-api-key" with your actual API key. Adjust tokens and parameters as needed.
Calculate accurate API costs for Gemini 3 Pro (Google). Estimate token pricing, input/output costs, context caching savings, and total expenses for your AI application.
$1.25/1M tokens
$10.00/1M tokens
$0.32/1M tokens
2,000,000
tokens supported
Gemini 3 Pro is ideal for applications requiring high throughput. With input pricing at $1.25 per 1M tokens, it's cost-effective for processing large volumes of text, images, videos, audio, making it suitable for content generation, data processing, and automated workflows.
With a context window of 2,000,000 tokens, Gemini 3 Pro excels at tasks requiring extensive context. Perfect for document analysis, long-form content generation, code review, and multi-turn conversations that span thousands of tokens.
Leverage context caching at $0.32 per 1M tokens to reduce costs for repeated inputs. Ideal for applications with recurring prompts, template-based generation, and batch processing where input context can be reused.
Enable context caching to reduce input costs from $1.25 to $0.32 per 1M tokens for repeated contexts.
Shorter, more focused prompts reduce token usage. Use system messages effectively and avoid redundant context to minimize input costs.
Track your input/output token ratios. If output costs are high, consider using Gemini 3 Profor initial processing and cheaper models for follow-up tasks.
Costs vary based on input/output tokens, caching usage, and additional features. Input tokens cost $1.25 per 1M tokens, while output tokens cost $10.00per 1M tokens. Use the calculator above to estimate costs for your specific use case.
Gemini 3 Pro supports up to 2,000,000 tokens in a single context window. This allows for processing of long documents, extensive conversations, and complex multi-step tasks without truncation.
Context caching allows you to reuse input context across multiple requests, reducing costs from $1.25 to $0.32 per 1M tokens. This is ideal for applications with repeated system prompts, templates, or shared context.
Yes! Gemini 3 Pro provides a standard API that can be integrated into any application. Check the developer code snippet below the calculator for Python and Node.js integration examples.