Gemini 2.5 Pro

Approved Data Classifications

Description

Gemini 2.5 Pro is a Google's newest multimodal AI model developed, designed to understand vast datasets and handle complex problems from different information sources, including text, audio, images, video and even entire code repositories. Its maximum winput token of 1,048,576 allows it to handle complex automated tasks via agentic workflows.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
gemini-2.5-flash	January 2025	Image, Text, Audio , Video	Text	>1,000,000	$2.50/1M input $1.25/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "gemini-2.5-pro",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="gemini-2.5-pro", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "gemini-2.5-pro",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

When to Use

• Premium reasoning and coding capabilities
• Handling extremely long contexts
• Best-in-class coding model
• Autonomous, multi-step workflows
• Multimodal input support

---

References

1. Google Gemini 2.5 Pro Report Card
   https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-pro
2. Google Gemini 2.5 Report
   https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf