Gemini 2.5 Pro

Google

google/gemini-2.5-pro

Gemini 2.5 Pro Experimental is Google's most advanced coding model yet and is state-of-the-art across a range of benchmarks requiring enhanced reasoning.

2.5 models are thinking models, capable of reasoning through thoughts before responding. The result is enhanced performance and improved accuracy.

This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

Capability

Vision Support

Tools

Function Calling

Context Window

1,048,576

Max Output Tokens

8,192

Language

Python JavaScript Curl

Using Gemini 2.5 Pro with Python API

Using Gemini 2.5 Pro 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-2.5-pro",
messages: [
  {
    role: 'user',
    content:
      'introduce your self',
    },
  ]
)
print(response)