Repository Public
1[Get a Gemini API Key](https://aistudio.google.com/apikey)23Gemini models can be used to advance foundational research across disciplines.4Here are ways that you can explore Gemini for your research:56- **Analyze and control model outputs** : For further analysis, you can examine a response candidate generated by the model using tools like `CitationMetadata`. You can also configure options for model generation and outputs, such as `responseSchema`, `topP`, and `topK`. [Learn more](https://ai.google.dev/api/generate-content).7- **Multimodal inputs** : Gemini can process images, audio, and videos, enabling a multitude of exciting research directions. [Learn more](https://ai.google.dev/gemini-api/docs/vision).8- **Long-context capabilities** : Gemini 3.0 Flash and Pro come with a 1-million-token context window. [Learn more](https://ai.google.dev/gemini-api/docs/long-context).9- **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, Gemini Enterprise Agent Platform can provide additional supporting infrastructure.1011To support academic research and drive cutting-edge research, Google provides12access to Gemini API credits for scientists and academic researchers through the13[Gemini Academic Program](https://ai.google.dev/gemini-api/docs/gemini-for-research#gemini-academic-program).1415## Get started with Gemini1617The Gemini API and Google AI Studio help you start working with Google's latest18models and turn your ideas into applications that scale.1920### Python2122 from google import genai2324 client = genai.Client()25 response = client.models.generate_content(26 model="gemini-3.8-flash",27 contents="How large is the universe?",28 )2930 print(response.text)3132### JavaScript3334 import { GoogleGenAI } from "@google/genai";3536 const ai = new GoogleGenAI({});3738 async function main() {39 const response = await ai.models.generateContent({40 model: "gemini-3.8-flash",41 contents: "How large is the universe?",42 });43 console.log(response.text);44 }4546 await main();4748### Java4950 import com.google.genai.Client;51 import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;52 import com.google.genai.gaos.models.interactions.CreateModelInteraction;53 import com.google.genai.gaos.models.interactions.InteractionsInput;54 import com.google.genai.gaos.models.interactions.Model;5556 Client client = new Client();57 CreateModelInteraction req = CreateModelInteraction.builder()58 .model(Model.of("gemini-3.8-flash"))59 .input(InteractionsInput.of("How large is the universe?"))60 .build();61 var interaction = client.interactions.create(CreateInteractionRequestBody.of(req)).interaction().get();62 System.out.println(interaction.outputText().orElse(""));6364### REST6566 curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash:generateContent" \67 -H "x-goog-api-key: $GEMINI_API_KEY" \68 -H 'Content-Type: application/json' \69 -X POST \70 -d '{71 "contents": [{72 "parts":[{"text": "How large is the universe?"}]73 }]74 }'7576## Featured academics7778 "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."79[Diyi Yang's Website](https://cs.stanford.edu/~diyiy/)  "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."80[Lerrel Pinto's Website](https://www.lerrelpinto.com/)8182## Gemini Academic Program8384Qualified academic researchers (such as faculty, staff, and PhD students) in [supported85countries](https://ai.google.dev/gemini-api/docs/available-regions) can apply to receive Gemini API86credits and higher rate limits for research projects. This support enables87higher throughput for scientific experiments and advances research.8889We are particularly interested in the research areas in the following section,90but we welcome applications from diverse scientific disciplines:9192- **Evaluations and benchmarks**: Community-endorsed evaluation methods that93 can provide a strong performance signal in areas such as factuality, safety,94 instruction following, reasoning, and planning.9596- **Accelerating scientific discovery to benefit humanity**: Potential97 applications of AI in interdisciplinary scientific research, including areas98 such as rare and neglected diseases, experimental biology, materials science,99 and sustainability.100101- **Embodiment and interactions**: Utilizing large language models to102 investigate novel interactions within the fields of embodied AI, ambient103 interactions, robotics, and human-computer interaction.104105- **Emergent capabilities**: Exploring new agentic capabilities required to106 enhance reasoning and planning, and how capabilities can be expanded during107 inference (e.g., by utilizing Gemini Flash).108109- **Multimodal interaction and understanding**: Identifying gaps and110 opportunities for multimodal foundational models for analysis, reasoning,111 and planning across a variety of tasks.112113Eligibility: Only individuals (faculty members, researchers or equivalent)114affiliated with a valid academic institution, or academic research organization115can apply. Note that API access and credits will be granted and removed116at Google's discretion. We review applications on a monthly basis.117118### Start researching with the Gemini API119120[Apply now](https://forms.gle/HMviQstU8PxC5iCt5)