GoogleModels
Google Gemini models and their capabilities. See https://ai.google.dev/gemini-api/docs for more information.
| Name | Speed | Price (per 1M tokens) | Input | Output |
|---|---|---|---|---|
| Gemini2_0Flash | Fast | $0.10-$ 0.70 / $0.40 | Audio, Image, Video, Text, Tools | Text, Tools |
| Gemini2_0Flash001 | Fast | $0.10-$ 0.70 / $0.40 | Audio, Image, Video, Text, Tools | Text, Tools |
| Gemini2_0FlashLite | Very fast | $0.075 / $ 0.30 | Audio, Image, Video, Text, Tools | Text, Tools |
| Gemini2_5Pro | Slow | $1.25-$ 2.50 /$10.00-$ 15.00² | Audio, Image, Video, Text, Tools | Text, Tools |
| Gemini2_5Flash | Medium | $0.15-$ 1.00 /$0.60-$ 3.50³ | Audio, Image, Video, Text, Tools | Text, Tools |
| Gemini2_5FlashLite | Fast | $0.10-$ 0.30 / $0.40 | Audio, Image, Video, Text, Tools | Text, Tools |
See also
Properties
Link copied to clipboard
Gemini 2.0 Flash is a fast, efficient model for a wide range of tasks. It's optimized for speed and efficiency.
Link copied to clipboard
Specific version of Gemini 2.0 Flash
Link copied to clipboard
Gemini 2.0 Flash-Lite is the smallest and most efficient model in the Gemini 2.0 family. Optimized for low-latency applications.
Link copied to clipboard
Specific version of Gemini 2.0 Flash-Lite
Link copied to clipboard
Gemini 2.5 Flash offers a balance of speed and capability.
Link copied to clipboard
A Gemini 2.5 Flash model optimized for cost-efficiency and high throughput.
Link copied to clipboard
Gemini 2.5 Pro offers advanced capabilities for complex tasks.