Back to all models
Get all the details on Gemini 2.5 Pro Preview, an AI model from Google. This page covers its token limits, pricing structure, key capabilities such as advanced_reasoning, coding, context_caching, available API code samples, and performance strengths.
Key Metrics
Input Limit
1M tokens
Output Limit
No data tokens
Input Cost
$1.25/1M
Output Cost
$10.00/1M
Sample API Code
import google.generativeai as genai
genai.configure(api_key='YOUR_API_KEY')
model = genai.GenerativeModel('gemini-2.5-pro-preview-0514') # Example model ID
response = model.generate_content('Write a short story about a robot learning to love.')
print(response.text)Required Libraries
google.generativeai
@google/generative-ai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1446 | lmarena.ai | Rank 1 overall | |
1420 | lmarena.ai | Rank 1 overall | |
1379 | lmarena.ai | Rank 1 overall | |
1142 | lmarena.ai | Rank 1 overall (model listed as gemini-2.5-pro-grounding) | |
82.1 | Vellum | Best in Adaptive Reasoning | |
92 | Vellum | Rank 3 in High School Math | |
84 | Vellum | Rank 2 in Reasoning | |
63.8 | Vellum | Rank 4 in Agentic Coding | |
78.99 | LiveBench | Rank 3 overall (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
88.25 | LiveBench | Rank 3 in Reasoning (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
72.87 | LiveBench | Rank 3 in Coding (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
88.63 | LiveBench | Rank 3 in Mathematics (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
68.85 | LiveBench | Rank 4 in Data Analysis (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
71.81 | LiveBench | Rank 6 in Language (model listed as Gemini 2.5 Pro Preview (2025-05-06)) | |
83.50 | LiveBench | Rank 7 in IF (model listed as Gemini 2.5 Pro Preview (2025-05-06)) |
Notes
Preview model, may change before becoming stable. Pricing is tiered based on prompt size.
Capabilities
advanced reasoning
coding
context caching
data analysis
instruction following
language understanding
long context
mathematics
multimodal input
thinking
vision
web browsing via tool
Supported Data Types
Input Types
text
image
video
audio
Output Types
text
Strengths & Weaknesses
Exceptional at
complex reasoning
coding
mathematics
data analysis
instruction following
web development
vision tasks
search grounding
general reasoning
Good at
language understanding
Additional Information
Latest Update
May 13, 2025
Knowledge Cutoff
No data