Google: Gemini 2.5 Flash
Google's Gemini 2.5 Flash is a strong all-round model with an impressive 1M token context window, full multimodal support (text, image, audio, video), and solid reasoning and coding benchmarks at a very competitive price. It's a well-rounded choice for businesses needing broad capability without premium costs, though it sits below the very top tier of the current generation.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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 accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).
Capabilities
Architecture
| Modality | Text + Image + File + Audio + Video → Text |
| Tokenizer | Gemini |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.30 | $0.000300 |
| Output | $2.50 | $0.002500 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
