Gemini 2.0 Flash (experimental)
The Gemini 2.0 Flash model builds upon the achievements of its predecessor, 1.5 Flash, which was widely regarded as a favorite among developers for its impressive performance and rapid response times. Notably, Gemini 2.0 Flash surpasses the 1.5 Pro model on key benchmarks while operating at double the speed. This upgraded version introduces several new capabilities. In addition to handling multimodal inputs such as images, video, and audio, it now supports multimodal outputs, including natively generated images combined with text and steerable multilingual text-to-speech (TTS) audio. Furthermore, Gemini 2.0 Flash can seamlessly integrate with external tools like Google Search, perform code execution, and leverage third-party user-defined functions.
Capability
Vision Support
Tools
Function Calling
Context Window
1,048,576
Max Output Tokens
8,192
Using Gemini 2.0 Flash (experimental) with Python API
Using Gemini 2.0 Flash (experimental) with OpenAI compatible API
import openai
client = openai.Client(
api_key= '{your_api_key}',
base_url="https://api.model.box/v1",
)
response = client.chat.completions.create(
model="google/gemini-2.0-flash-exp",
messages: [
{
role: 'user',
content:
'introduce your self',
},
]
)
print(response)