| gemini-2.5-flash |
5 |
250,000 |
20 |
A fast and lightweight model for general-purpose tasks. |
| gemini-2.5-flash-lite |
10 |
250,000 |
20 |
An even faster and more lightweight version of gemini-2.5-flash. |
| gemini-2.5-flash-tts |
3 |
10,000 |
10 |
Text-to-speech model based on gemini-2.5-flash. |
| gemini-2.5-pro |
0 |
0 |
0 |
A high-quality model for complex tasks. |
| gemini-2.5-pro-tts |
0 |
0 |
0 |
Text-to-speech model based on gemini-2.5-pro. |
| gemini-3-flash |
5 |
250,000 |
20 |
A fast and lightweight model for general-purpose tasks. |
| gemini-3.1-flash-lite |
15 |
250,000 |
500 |
An even faster and more lightweight version of gemini-3.1-flash. |
| gemini-3.1-pro |
0 |
0 |
0 |
A high-quality model for complex tasks. |
| gemini-3.1-flash-tts |
3 |
10,000 |
10 |
Text-to-speech model based on gemini-3.1-flash. |
| gemini-3.5-flash |
5 |
250,000 |
20 |
A fast and lightweight model for general-purpose tasks. |
| gemini-3.5-flash-lite |
15 |
250,000 |
500 |
An even faster and more lightweight version of gemini-3.5-flash. |
| gemini-3.6-flash |
5 |
250,000 |
20 |
A fast and lightweight model for general-purpose tasks. |
| gemini-2-flash |
0 |
0 |
0 |
A fast and lightweight model for general-purpose tasks. |
| gemini-2-flash-lite |
0 |
0 |
0 |
An even faster and more lightweight version of gemini-2-flash. |
| gemini-embedding-1 |
100 |
30,000 |
1,000 |
Model for generating embeddings for text data. |
| gemini-embedding-2 |
100 |
30,000 |
1,000 |
Model for generating embeddings for text data. |
| gemma-4-26b |
30 |
16,000 |
1,440 |
An open model for general-purpose tasks. |
| gemma-4-31b |
30 |
16,000 |
1,440 |
An open model for general-purpose tasks. |
| antigravity |
60 |
100,000 |
100 |
A model for creative writing and storytelling. |
| deep-research-pro-preview |
0 |
0 |
0 |
A model for deep research and analysis. |
| computer-use-preview |
0 |
0 |
0 |
A model for computer-related tasks. |
| gemini-robotics-er-1.5-preview |
10 |
250,000 |
20 |
A model for robotics and embodied reasoning. |
| gemini-robotics-er-1.6-preview |
5 |
250,000 |
20 |
A model for robotics and embodied reasoning. |
| gemini-omni-flash-preview |
0 |
0 |
0 |
A model for multimodal understanding. |
| gemini-2.5-flash-image |
0 |
0 |
0 |
A model for understanding and generating images. |
| gemini-3-pro-image |
0 |
0 |
0 |
A model for understanding and generating images. |
| gemini-3-pro-image-preview |
0 |
0 |
0 |
A model for understanding and generating images. |
| gemini-3.1-flash-image |
0 |
0 |
0 |
A model for understanding and generating images. |
| gemini-3.1-flash-image-preview |
0 |
0 |
0 |
A model for understanding and generating images. |
| gemini-3.1-flash-lite-image |
0 |
0 |
0 |
A model for understanding and generating images. |
| imagen-4-fast |
null |
null |
25 |
A fast image generation model. |
| imagen-4 |
null |
null |
25 |
A high-quality image generation model. |
| imagen-4-ultra |
null |
null |
25 |
An ultra-high-quality image generation model. |
| veo-3 |
0 |
null |
0 |
A model for generating videos. |
| veo-3-fast |
0 |
null |
0 |
A fast video generation model. |
| veo-3-lite |
0 |
null |
0 |
A lightweight video generation model. |
| lyria-3-clip |
0 |
0 |
0 |
A model for audio understanding. |
| lyria-3-pro |
0 |
0 |
0 |
A high-quality model for audio generation. |