| Description | Next-generation fast-response model for low-latency, high-throughput use cases | Most advanced Gemini model | Versatile and fast | Lightweight and efficient | Cost-effective for simple tasks | Previous generation advanced model |
| Best for | High-throughput applications and real-time interactions | Complex tasks requiring deep understanding | High-throughput applications | Quick responses and efficient processing | Budget-friendly tasks | Complex reasoning and analysis |
| Vision capability | Yes | Yes | No | No | No | Yes |
| Context window | 1.05M tokens | 1M tokens | 1M tokens | 1M tokens | 1M tokens | 1M tokens |
| API model key | gemini-3-flash-preview | gemini-2.5-pro | gemini-2.5-flash | gemini-2.5-flash-lite | gemini-2.0-flash-001
gemini-2.0-flash-thinking-exp-01-21
gemini-2.0-flash-exp | gemini-1.5-pro-preview-0409
gemini-1.5-pro |