Gemini 2.0 Flash Lite
Mid-TierMultimodalAPI Available
Benchmark Scores
75.2/100MMLU80.2
HumanEval78.5
Math65
Reasoning74.3
Coding77.8
About Gemini 2.0 Flash Lite
Gemini 2.0 Flash Lite is Google's most cost-efficient model, designed for high-throughput, low-latency applications where cost is the primary concern. It handles simple text tasks well at minimal cost.
Strengths
- +Cheapest Gemini model
- +Fast latency
- +Good for simple tasks
- +Large context window
Weaknesses
- -Weakest Gemini model overall
- -Poor on complex reasoning
- -Text-only output
Pricing
Per 1M tokens
Input$0.075
Output$0.30
Quick Facts
- Context Window
- 1M
- Parameters
- Undisclosed
- Release Date
- 2025-02-05
- Category
- Mid-Tier
Compare Models
See how Gemini 2.0 Flash Lite stacks up against other models