Preview
Gemini 2.5 FlashBest for fast performance on complex tasks
Try in Google AI Studio2.5 Flash is our fast, cost-efficient, thinking model.
Speed and value at scaleIdeal for tasks like summarization, chat applications, data extraction, and captioning.
Balance performance and your budget
Control how much 2.5 Flash reasons to reduce latency and cost.
Natively multimodal
Understands input across text, audio, images and video.
Long context
Explore vast datasets with a 1-million token context window.
Calibrated
The model applies appropriate thinking strategies across diverse scenarios, leading to more accurate and relevant outputs.
Controllable
Developers gain fine-grained control over the model's thinking process, allowing them to manage resource usage.
Adaptive
When no thinking budget is set, the model is still able to assess the complexity of a task and calibrates the amount of thinking accordingly.
2.0 Flash is now broadly available with multimodal reasoning and native tool use.
Native in, native outExperimental
Native image generation
Create or edit images and seamlessly blend them with text.
Watch demo
Coming soon
Native text-to-speech
Easily steer Gemini’s speaking style to match any mood.
Watch demo
Available now
Native tool use
Build agents that use Google Search, code execution and more.
Watch demo
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.3