Key Metrics
Input Limit
1.0M tokens
Output Limit
65.5K tokens
Input Cost
$1.25/1M
Output Cost
$10.00/1M
Sample API Code
import google.generativeai as genai
# Configure the API key
genai.configure(api_key="YOUR_API_KEY")
# Set up the model
model = genai.GenerativeModel('gemini-2.5-pro-preview-05-06')
# Generate content
response = model.generate_content("Explain the difference between transformers and RNNs in deep learning.")
print(response.text)Required Libraries
google-generativeai
@google/generative-ai
Notes
State-of-the-art thinking model capable of reasoning over complex problems in code, math, and STEM. Can analyze large datasets, codebases, and documents using long context. Supports caching.
Capabilities
Multimodal input
Long context
Function calling
JSON mode
Advanced reasoning
System instructions
Code execution
Document understanding
Caching
Supported Data Types
Input Types
text
image
audio
video
Output Types
text
Strengths & Weaknesses
Exceptional at
Complex reasoning
Multimodal
Code generation
Good at
Long context
Instruction following
Additional Information
Latest Update
May 6, 2024
Knowledge Cutoff
2025-01
ELO Score
1448