Gemini 2.5 Flash
GeminiCompact
ThinkingTool UseVisionStructured Output
About this model
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
Performance Tier
Compact
Gemini 2.5 Flash is a compact model from Gemini : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.300 |
| Output (completion) | $2.50 |
| Image | $0.300 |
| Internal reasoning | $2.50 |
| Cache read | $0.030 |
| Cache write | $0.083 |
Capabilities
Context Length1.0M
Max Output Tokens66K
TokenizerGemini
Inputfile, image, text, audio, video
Outputtext
Release DateJune 17, 2025
Benchmarks
General Intelligence
MMLU
83.8%
Mathematics
MATH-500
85.8%
AIME 2025
72%
Programming
HumanEval
82%
Reasoning
Humanity's Last Exam
11%
Recommended Use Cases
General ChatCodingSummarizationData ExtractionCustomer Support
Strengths
- Excellent price-to-performance ratio with thinking capabilities
- Fast inference suitable for real-time applications
- 1M token context at a fraction of Pro pricing
- Built-in thinking mode for harder problems
Limitations
- Significantly less capable than Gemini 2.5 Pro on complex tasks
- Lower coding performance (SWE-bench 49.2%)
Resources
This model may use your data for training
