Google Gemini Developer API Free Tier

Overview

The Google Gemini Developer API Free Tier provides developers and small projects with no-cost access to Google's suite of Gemini models through Google AI Studio. It allows developers to prototype, experiment, and integrate state-of-the-art multimodal AI into applications without requiring an upfront financial commitment or paid tier subscription.

Key Features

• Free Input & Output Tokens: Enjoy free prompt input, cached tokens, and generation outputs within defined rate limits across supported models.
• Google AI Studio Integration: Web-based developer playground for prompt prototyping, testing system instructions, and generating API keys.
• Multimodal Processing: Native support for text, code execution, audio, image, and video inputs depending on model capabilities.
• Context Caching: Free context caching on supported Flash variants (such as Gemini 3.8 Flash, 3.7 Flash, and 3.6 Flash).
• Tool Support: Includes access to Code Execution and URL Context free of charge. Search grounding and Google Maps grounding offer complimentary monthly quotas (e.g., up to 500 RPD on selected Gemini 2.5 models).

Included Models

• Flagship Reasoning & Coding: Gemini 2.5 Pro, Gemini 3.8 Flash, Gemini 3.7 Flash
• High-Efficiency & Agentic Workloads: Gemini 3.6 Flash, Gemini 3.5 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite
• Speech & Live Dialogue: Gemini 3.5 Transcribe, Gemini 3.5 Live Translate, Gemini 3.1 Flash Live Preview, Gemini 2.5 Flash Native Audio
• Open Weights: Gemma 4

Usage Terms & Privacy

• Product Improvement: Content submitted via the Free Tier may be reviewed by human reviewers and used to train and improve Google products and services. Applications handling strictly confidential or proprietary user data should consider upgrading to the Paid Tier.
• Rate Limits: Usage is subject to Requests Per Minute (RPM) and Requests Per Day (RPD) limits.