Back to all models
Get all the details on Gemini 1.5 Flash, an AI model from Google. This page covers its token limits, pricing structure, key capabilities such as context_caching, grounding_with_google_search, long_context, available API code samples, and performance strengths.
Key Metrics
Input Limit
1M tokens
Output Limit
1M tokens
Input Cost
$0.07/1M
Output Cost
$0.30/1M
Sample API Code
import google.generativeai as genai; genai.configure(api_key='YOUR_API_KEY'); model = genai.GenerativeModel(model_name='gemini-1.5-flash-latest'); prompt_response = model.generate_content('Write a story about a magic backpack.'); print(prompt_response.text)Required Libraries
google-generativeai
@google/generative-ai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1227 | lmarena.ai | - | |
1072 | lmarena.ai | - |
Notes
Our fastest multimodal model with great performance for diverse, repetitive tasks and a 1 million token context window. Pricing is tiered based on prompt size (<= 128k tokens vs > 128k tokens).
Capabilities
context caching
grounding with google search
long context
multimodal input
tuning
Supported Data Types
Input Types
text
image
video
audio
Output Types
text
Strengths & Weaknesses
Exceptional at
long context processing
multimodal understanding
diverse tasks
repetitive tasks
speed
Additional Information
Latest Update
May 13, 2025
Knowledge Cutoff
No data