Author's Description
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. Note: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the ":thinking" suffix), the model will explicitly avoid generating thinking tokens. To utilize the thinking capability and receive thinking tokens, you must choose the ":thinking" variant, which will then incur the higher thinking-output pricing. 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).
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Google's Gemini 2.5 Flash Preview 04-17 demonstrates strong overall performance, positioning itself as a robust workhorse model. It performs among the fastest models, ranking in the 68th percentile for speed, and offers competitive pricing, placing in the 60th percentile. Notably, its reliability is exceptional, achieving a perfect 100th percentile, indicating consistent and dependable operation with minimal technical failures. Across benchmark categories, Gemini 2.5 Flash exhibits particular strengths in classification and knowledge-based tasks. It achieved perfect accuracy in Email Classification, making it the most accurate model at its price point and among models of comparable speed. Its General Knowledge and Ethics performance were also very strong, with 99.3% and 99.0% accuracy respectively. While its Reasoning and Coding (Baseline) accuracy were solid at 82.0% and 83.0%, these benchmarks also represented its higher cost and duration metrics. The model's built-in "thinking" capabilities, though incurring higher costs, are designed to enhance accuracy and contextual understanding, which likely contributes to its strong performance in complex reasoning tasks.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.15 |
Completion | $0.6 |
Input Cache Read | $0.0375 |
Input Cache Write | $0.233 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Google
|
Google | google/gemini-2.5-flash-preview-04-17 | 1M | $0.15 / 1M tokens | $0.6 / 1M tokens |
Google AI Studio
|
Google AI Studio | google/gemini-2.5-flash-preview-04-17 | 1M | $0.15 / 1M tokens | $0.6 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by google
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Google: Gemini 2.5 Flash Lite | Jul 22, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★★★★★ | ★★★ | $$$ |
Google: Gemini 2.5 Flash Lite Preview 06-17 | Jun 17, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★★★★ | ★★★ | $$$ |
Google: Gemini 2.5 Flash | Jun 17, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★★★ | ★★★★★ | $$$$$ |
Google: Gemini 2.5 Pro | Jun 17, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★ | ★★★★★ | $$$$$ |
Google: Gemini 2.5 Pro Preview 06-05 | Jun 05, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★ | ★★★★★ | $$$$$ |
Google: Gemma 1 2B Unavailable | May 28, 2025 | 2B | 8K |
Text input
Text output
|
— | — | $$ |
Google: Gemma 3n 4B | May 20, 2025 | 4B | 32K |
Text input
Text output
|
★★★ | ★★★ | $ |
Google: Gemini 2.5 Flash Preview 05-20 Unavailable | May 20, 2025 | — | 1M |
File input
Text input
Image input
Text output
|
★★★★ | ★★★★★ | $$$ |
Google: Gemini 2.5 Pro Preview 05-06 | May 06, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★ | ★★★★★ | $$$$$ |
Google: Gemini 2.5 Pro Experimental | Mar 25, 2025 | — | 1M |
File input
Text input
Image input
Text output
|
— | — | $ |
Google: Gemma 3 4B | Mar 13, 2025 | 4B | 131K |
Text input
Image input
Text output
|
★★★ | ★★ | $ |
Google: Gemma 3 12B | Mar 13, 2025 | 12B | 131K |
Text input
Image input
Text output
|
★★ | ★★ | $$ |
Google: Gemma 3 27B | Mar 11, 2025 | 27B | 131K |
Text input
Image input
Text output
|
★★ | ★★★ | $$ |
Google: Gemini 2.0 Flash Lite | Feb 25, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★★★★★ | ★★ | $$ |
Google: Gemini 2.0 Flash | Feb 05, 2025 | — | 1M |
Audio input
File input
Text input
Image input
Text output
|
★★★★★ | ★★★ | $$ |
Google: Gemini 1.5 Flash 8B | Oct 02, 2024 | ~500B | 1M |
Text input
Image input
Text output
|
★★★★★ | ★★ | $$ |
Google: Gemma 2 27B | Jul 12, 2024 | 27B | 8K |
Text input
Text output
|
★★★★★ | ★★ | $$$$ |
Google: Gemma 2 9B | Jun 27, 2024 | 9B | 8K |
Text input
Text output
|
★★★★★ | ★ | $$ |
Google: Gemini 1.5 Flash | May 13, 2024 | ~500B | 1M |
Text input
Image input
Text output
|
★★★★★ | ★★★ | $$ |
Google: Gemini 1.5 Pro | Apr 08, 2024 | ~1T | 2M |
Text input
Image input
Text output
|
★★★ | ★★★ | $$$$ |