Back to all models
Get all the details on Gemini 1.5 Pro, an AI model from Google. This page covers its token limits, pricing structure, key capabilities such as audio_understanding, code_execution, document_understanding, available API code samples, and performance strengths.
Key Metrics
Input Limit
2M tokens
Output Limit
No data tokens
Input Cost
$1.25/1M
Output Cost
$5.00/1M
Sample API Code
import google.generativeai as genai
genai.configure(api_key='YOUR_API_KEY')
generation_config = {
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"max_output_tokens": 8192,
"response_mime_type": "text/plain",
}
safety_settings = [
{
"category": "HARM_CATEGORY_HARASSMENT",
"threshold": "BLOCK_MEDIUM_AND_ABOVE",
},
{
"category": "HARM_CATEGORY_HATE_SPEECH",
"threshold": "BLOCK_MEDIUM_AND_ABOVE",
},
{
"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
"threshold": "BLOCK_MEDIUM_AND_ABOVE",
},
{
"category": "HARM_CATEGORY_DANGEROUS_CONTENT",
"threshold": "BLOCK_MEDIUM_AND_ABOVE",
},
]
model = genai.GenerativeModel(
model_name="gemini-1.5-pro-latest",
generation_config=generation_config,
safety_settings=safety_settings,
)
chat_session = model.start_chat(
history=[
]
)
response = chat_session.send_message("Tell me a story about a magic backpack.")
print(response.text)Required Libraries
google-generativeai
@google/generative-ai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1302 | OpenLLM Leaderboard | Score for gemini-1.5-pro-002 | |
893 | OpenLLM Leaderboard | Score for Gemini-1.5-Pro-002 | |
1222 | OpenLLM Leaderboard | Score for gemini-1.5-pro-002 |
Notes
Pricing is tiered based on prompt size. Prices may differ on Vertex AI. Features a breakthrough 2 million token context window.
Capabilities
audio understanding
code execution
document understanding
function calling
grounding with google search
image understanding
long context
multimodal input
structured output
thinking
video understanding
Supported Data Types
Input Types
text
image
video
audio
document
Output Types
text
json
code
Strengths & Weaknesses
Exceptional at
long context processing
complex reasoning
coding
Good at
multimodal understanding
general purpose
Additional Information
Latest Update
May 13, 2025
Knowledge Cutoff
No data