New Gemini 2.5 Flash and Flash-Lite models just shipped

Upgrade to better and more cost-effective models.

                                                    ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏  ‍͏  ͏ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­ ͏‌ ­ ­ ­ ­  

Email not displaying correctly? View it online

More cost-effective and enhanced Gemini 2.5 Flash family models

Upgrade to the latest 2.5 Flash

Hi 勇汀, We just shipped two new Gemini 2.5 models (Flash and Flash-Lite) that are more intelligent, cost-effective, and token-efficient to address critical feedback we received from developers like you.

Gemini 2.5 Flash This model is now much more effective at using tools like Search and Code Execution. With thinking on, it is also more cost-efficient, achieving higher quality outputs while using fewer tokens.

Gemini 2.5 Flash-Lite This model now outperforms Gemini 2.0 Flash, based on our internal evaluations. It's cheaper, lower latency, less verbose, and delivers major quality improvements in instruction following, image understanding, and long-context performance.

Gemini 2.5 Flash This model is now much more effective at using tools like Search and Code Execution. With thinking on, it is also more cost-efficient, achieving higher quality outputs while using fewer tokens.

Gemini 2.5 Flash-Lite This model now outperforms Gemini 2.0 Flash, based on our internal evaluations. It's cheaper, lower latency, less verbose, and delivers major quality improvements in instruction following, image understanding, and long-context performance.

Update your model in seconds To use it, simply specify the versioned model string in your API call: gemini-2.5-flash-preview-09-2025 gemini-2.5-flash-lite-preview-09-2025 Use the -latest alias to always point to our most recent model versions: gemini-flash-latest gemini-flash-lite-latest You can use our SDKs for Python, JavaScript, and Go, or make a direct REST API call with cURL. Get your API key and update the model in seconds.

from google import genai client = genai.Client() prompt = """ You are playing the 20 question game. You know that what you are looking for is an aquatic mammal that doesn't live in the sea, is venomous and that's smaller than a cat. What could that be and how could you make sure? """ # Start the generation job response = client.models.generate_content(     model="gemini-2.5-flash-preview-09-2025",     contents=prompt ) print(response.text)

For comprehensive details on all features, model comparisons, and guidance on selecting the optimal model for your requirements, check out our Gemini models documentation.

Happy building,  The Google AI Studio team

Prompt models

Manage API keys

Get help

Prompt models Manage API keys Get help

Stay connected

© 2025 Google LLC 1600 Amphitheatre Parkway, Mountain View, CA 94043, USA This email was sent to pudding@g.nccu.edu.tw because you signed up to receive emails about Google AI. If you do not wish to receive these emails, please unsubscribe.