KI & Multimodalllmmultimodalvisiongoogle
Google Gemini API
Die Google Gemini API verbindet Text, Bild und Audio in einem multimodalen Modell – ideal für Vision-, Analyse- und Assistenz-Anwendungen.
- Provider
- Pricing
- Free quota, then per token
- Authentication
- API key or OAuth
- API key
- Required
Get started
Start building with Google
Create an account, get your API key and start integrating Google Gemini API.
Technical details
- Endpoint
https://generativelanguage.googleapis.com/v1beta- Authentication
- API key or OAuth
- Rate limit
- Quota-based limits
- SDKs
- PythonJavaScriptGoJava
- Documentation
- Open official docs
Details
- Features
- Multimodal input from text, image and audioLarge context windowsIntegration with Google CloudFunction calling and structured output
- Use case
- Image analysis, document processing and multimodal assistants
- Website
- https://ai.google.dev