Back to projectPublic page

Gemini Developer API Pricing

6 concepts • medium difficulty

Part of TEST

16 blocks0 nested pages
Last updated Jan 10, 2026. Clone to remix or explore the blocks below.
7c6ce94c...
2346b3d2...
concept

Introduction to Gemini API Pricing Plans

Provide a concise overview of the three main pricing plans for the Gemini API: Free, Paid, and Enterprise. For each plan, describe its target audience (e.g., developers, production apps, large-scale deployments) and highlight its key features and differentiators, such as access to specific models, content usage policy (improving products or not), rate limits, and integration with Vertex AI. Cover content from the 'Pricing Plans' section on page 1.

Gemini API Pricing Plans

Understanding the Gemini API pricing helps you choose the right plan. There are three main options: Free, Paid, and Enterprise. Each plan is designed for different needs and offers unique features.

Free Plan

This plan is perfect for developers and small projects just starting out. It lets you explore the Gemini API without any cost.

  • Access to specific, limited models.
  • Free input and output tokens.
  • Includes access to Google AI Studio.

Important: Content you use with the Free plan helps improve Google's products.

Paid Plan

The Paid plan is for production applications that need more power and higher usage. It's great for apps ready for real users.

  • Higher rate limits for production use.
  • Access to context caching and Batch API (which can save 50% on costs).
  • You get Google's most advanced models.

Important: With the Paid plan, your content is NOT used to improve Google's products.

Enterprise Plan

This plan is built for large-scale deployments and big companies. It offers advanced features through Vertex AI.

  • Includes all features from the Paid plan.
  • Optional access to dedicated support.
  • Enhanced security and compliance features.
  • Offers provisioned throughput and volume-based discounts.
  • Integrates with ML ops and Model Garden for advanced operations.
fe3c1e1e...
2b7bdbde...
vocabulary

Key Vocabulary: Gemini API Pricing

Create a flashcard deck for essential terms related to Gemini API pricing. Terms to include: 'Tokens (Input/Output)', 'Context Caching', 'Batch API', 'Grounding', 'RPD (Requests Per Day)', 'Thought Tokens', 'Multimodal Understanding', 'Agentic Model', 'Vibecoding Model', 'Provisioned Throughput'. Provide clear and concise definitions for each term based on their usage throughout the chapter (pages 1-6).

1 / 0
Click to reveal
3fbb8006...
concept

Deep Dive: Gemini 3 Pro Preview Model

Introduce the Gemini 3 Pro Preview model. Explain its Model ID (`gemini-3-pro-preview`), its primary capabilities (world's best for multimodal understanding, powerful agentic and vibecoding model), and its general purpose. Mention where users can try it. Cover the introductory text for 'Gemini 3 Pro Preview' on page 2.

Gemini 3 Pro Preview

Meet the Gemini 3 Pro Preview model! It's identified by its unique ID: gemini-3-pro-preview.

This model is truly special. It's considered the world's best for multimodal understanding. This means it can understand and work with many different kinds of information at the same time, like text, images, and more.

It's also our most powerful agentic and vibecoding model. This makes it great for complex tasks that need deep understanding and smart actions.

Want to try it out? You can explore the Gemini 3 Pro Preview model in Google AI Studio today!

Try it here

26966804...
adbb9d21...
quiz

Quiz: Gemini 3 Pro Pricing Details

Create 3-4 multiple-choice questions to test understanding of Gemini 3 Pro Preview pricing. Questions should cover: 1) The difference in Input/Output pricing for Paid Tier based on prompt token count (e.g., 200,000 token threshold), 2) The cost of Context Caching storage, 3) The status of Grounding via Google Search (free limits, future billing), and 4) The content usage policy for Free vs. Paid tiers. All questions should refer to the 'Gemini 3 Pro Preview' section on page 2.

0 / 4

For the Gemini 3 Pro Preview model, if a Paid Tier user sends a standard prompt with 250,000 tokens, how does the input price per million tokens compare to a prompt with 150,000 tokens?