Accelerate discovery with Gemini for Research

Gemini models can be used to advance foundational research across disciplines. Here are ways that you can explore Gemini for your research:

• Fine-tuning: You can fine-tune Gemini models for a variety of modalities to advance your research. Learn more.
• Analyze and control model outputs: For further analysis, you can examine a response candidate generated by the model using tools like Logprobs and CitationMetadata. You can also configure options for model generation and outputs, such as responseSchema, topP, and topK. Learn more.
• Multimodal inputs: Gemini can process images, audio, and videos, enabling a multitude of exciting research directions. Learn more.
• Long-context capabilities: Gemini 1.5 Flash comes with a 1-million-token context window, and Gemini 1.5 Pro comes with a 2-million-token context window. Learn more.
• Grow with Google: Quickly access Gemini models through the API and Google AI Studio for production use cases. If you're looking for a Google Cloud-based platform, Vertex AI can provide additional supporting infrastructure.

To support academic research and drive cutting-edge research, Google provides access to Gemini API credits for scientists and academic researchers through the Gemini Academic Program.

Get started with Gemini

The Gemini API and Google AI Studio help you start working with Google's latest models and turn your ideas into applications that scale.

import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel("gemini-1.5-flash")
response = model.generate_content("How large is the universe?")
print(response.text)

const { GoogleGenerativeAI } = require("@google/generative-ai");

const genAI = new GoogleGenerativeAI("YOUR_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const prompt = "How large is the universe?";

const result = await model.generateContent(prompt);
console.log(result.response.text());

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=YOUR_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
  "contents": [{
    "parts":[{"text": "How large is the universe?"}]
    }]
   }'

Featured academics

"Our research investigates Gemini as a visual language model (VLM) and its agentic behaviors in diverse environments from robustness and safety perspectives. So far, we have evaluated Gemini's robustness against distractions such as pop-up windows when VLM agents perform computer tasks, and have leveraged Gemini to analyze social interaction, temporal events as well as risk factors based on video input."

"Gemini Pro and Flash, with their long context window, have been helping us in OK-Robot, our open-vocabulary mobile manipulation project. Gemini enables complex natural language queries and commands over the robot's "memory": in this case, previous observations made by the robot over a long operation duration. Mahi Shafiullah and I are also using Gemini to decompose tasks into code that the robot can execute in the real world."

Gemini Academic Program

Qualified academic researchers (such as faculty, staff, and PhD students) in supported countries can apply to receive Gemini API credits and higher rate limits for research projects. This support enables higher throughput for scientific experiments and advances research.

We are particularly interested in the research areas in the following section, but we welcome applications from diverse scientific disciplines:

• Evaluations and benchmarks: Community-endorsed evaluation methods that can provide a strong performance signal in areas such as factuality, safety, instruction following, reasoning, and planning.

• Accelerating scientific discovery to benefit humanity: Potential applications of AI in interdisciplinary scientific research, including areas such as rare and neglected diseases, experimental biology, materials science, and sustainability.

• Embodiment and interactions: Utilizing large language models to investigate novel interactions within the fields of embodied AI, ambient interactions, robotics, and human-computer interaction.

• Emergent capabilities: Exploring new agentic capabilities required to enhance reasoning and planning, and how capabilities can be expanded during inference (e.g., by utilizing Gemini Flash).

• Multimodal interaction and understanding: Identifying gaps and opportunities for multimodal foundational models for analysis, reasoning, and planning across a variety of tasks.

Eligibility: Only individuals (faculty members, researchers or equivalent) affiliated with a valid academic institution, or academic research organization can apply. Note that API access and credits will be granted and removed at Google's discretion. We review applications on a monthly basis.