Major Release Google · Released
Gemini 2.0 Flash
What is Gemini 2.0 Flash?
Gemini 2.0 Flash is a Major Release AI model from Google, released on December 11, 2024. It has a 1M tokens context window, costs $0.10 per million input tokens, and scores 91.1% on MATH-500. It is available via the company's API.
First Gemini 2 model — fast, cheap, multimodal, with tool use native.
Google's next-generation model with native multimodal capabilities
Key features
- Native multimodal generation
- Real-time API
- Agentic capabilities
- Enhanced speed
How much does Gemini 2.0 Flash cost?
| Metric | Price |
|---|---|
| input per mtok | $0.10 |
| output per mtok | $0.40 |
| cache read per mtok | $0.03 |
Pricing data verified .
What context window does Gemini 2.0 Flash have?
- Context window
- 1M tokens
- Max output
- 8K
- Input modalities
- text, image, audio, video
- Output modalities
- text, image, audio
How does Gemini 2.0 Flash score on benchmarks?
| Benchmark | Score |
|---|---|
| MMLU-Pro | 78.2% |
| MMMU | 70.7% |
| LiveCodeBench | 21.0% |
| GPQA Diamond | 63.6% |
| HumanEval | 90.7% |
| MATH-500 | 91.1% |
| AIME 2025 | 30.0% |
| HLE | 4.7% |
| SciCode | 34.0% |
| TAU2-bench | 29.5% |
| TerminalBench-Hard | 3.8% |
| IF-Bench | 40.2% |
| LiveCodeBench Reasoning | 28.3% |
| AA Intelligence Index | 16.8 |
Benchmark scores verified .