Gemini 2.5 Flash
Gemini 2.5 Flash is a large language model made by Google, added to the catalog on 17 Jun 2025. It has a context window of 1,048,576 tokens and costs $0.30 per 1M input tokens and $2.50 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: enhance scientific research accuracy, improve coding project efficiency and facilitate complex mathematical problem-solving.
Price checked ยท source: OpenRouter
What Gemini 2.5 Flash is
Google's Gemini 2.5 Flash, released on June 17, 2025, is a versatile model designed to handle complex reasoning, coding, and scientific tasks. With a substantial context window of 1,048,576 tokens, it processes text and images to generate precise text outputs. This model supports various input modalities, including files, images, text, and audio, making it adaptable for diverse applications. Key features include its advanced reasoning capabilities and the flexibility to configure parameters like 'max tokens for reasoning'. Whether for scientific research or intricate coding projects, Gemini 2.5 Flash offers nuanced context handling and accurate responses.
Key features
- Advanced reasoning capabilities
- Configurable reasoning tokens
- Handles text and image inputs
- Large context window of 1,048,576 tokens
- Supports diverse input modalities
Typical uses
- Enhance scientific research accuracy
- Improve coding project efficiency
- Facilitate complex mathematical problem-solving
- Streamline data analysis tasks
Gemini 2.5 Flash pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.30 |
| Output, per 1M tokens | $2.50 |
| Cached input read, per 1M tokens | $0.03 |
| Cache write, per 1M tokens | $0.0833 |
| Image input, per image | $0.00 |
| Web search, per search | $0.014 |
No price change since it was added on 17 Jun 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0009 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0095 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.014 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.049 |
Gemini 2.5 Flash specifications
| Model id | google/gemini-2.5-flash |
|---|---|
| Version | gemini-2.5-flash |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 65,535 tokens |
| Knowledge cutoff | 2025-01-31 |
| Added to catalog | 17 Jun 2025 |
| Input types | file, image, text, audio, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI promises a future where work is less about drudgery and more about purpose. Repetitive tasks will be automated, freeing human intellect for complex problem-solving, strategic thinking, and innovation. This shift could lead to shorter workweeks and more flexible schedules, fostering a better work-life balance. Leisure will be enriched by personalized experiences. AI-powered recommendations will curate entertainment, travel, and learning opportunities tailored to individual preferences, making downtime more fulfilling. Imagine virtual reality experiences indistinguishable from reality, or AI companions for learning new skills. Creativity will be amplified, not replaced. AI can act as a powerful co-creator, generating novel ideas, refining artistic techniques, and even composing music or writing poetry. Artists and designers will leverage AI to explore new frontiers, pushing the boundaries of human imagination and producing unprecedented works. This symbiotic relationship will usher in an era of unparalleled human expression.
Compare Gemini 2.5 Flash
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.