Available Google AI Models Overview.
Gemini
The following Gemini models are available in the Giselle workspace. Each model offers specific capabilities and features to match your use case requirements.
| Models | Generate Text | Web Search | Reasoning | Input PDF | Input Image | Input Audio | Input Video | Context Window | Plan@Giselle |
|---|---|---|---|---|---|---|---|---|---|
| gemini-2.5-pro-exp-03-25 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 1M tokens (2M soon) | Free |
| gemini-2.5-pro-preview-03-25 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 1M tokens (2M soon) | Pro |
| gemini-2.5-flash-preview-04-17 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 1M tokens | Pro |
| gemini-2.0-flash | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | 1M tokens | Free |
| gemini-2.0-flash-thinking-exp-01-21 | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | 1M tokens | Free |
| gemini-2.0-pro-exp-02-05 | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | 1M tokens | Free |
Note: Some features may not be available within Giselle even if they are offered in the Google official API. Features marked ‘Free’ or ‘Pro’ refer to the Giselle subscription plan required to access them.
gemini-2.5-pro-exp-03-25
The latest comprehensive model supporting all features, with state-of-the-art capabilities. It offers text generation, web search, advanced reasoning, and robust coding features. It supports a wide range of input formats including PDF, images, audio, and video, and includes a context window of up to 1 million tokens (with expansion to 2 million tokens planned). Ideal for handling complex problems, deep multimodal understanding, and tasks requiring extensive data analysis. Available on the Free plan.
gemini-2.5-pro-preview-03-25
A preview version of the next-generation comprehensive model, offering early access to cutting-edge features. It provides state-of-the-art capabilities similar to gemini-2.5-pro-exp-03-25, including text generation, web search, advanced reasoning, and robust coding features. It supports a wide range of input formats (PDF, images, audio, video) and has a 1 million token context window (expansion planned). Ideal for users wanting to experiment with the latest advancements for complex problems and deep multimodal understanding. Requires a Pro plan.
gemini-2.5-flash-preview-04-17
A preview version of the next-generation Flash model, optimized for speed and reasoning. It offers fast text generation, web search, reasoning capabilities, and supports various inputs (PDF, images, audio, video). With a 1 million token context window, it’s ideal for tasks requiring quick responses combined with analytical depth and multimodal understanding. Requires a Pro plan.
gemini-2.0-flash
Previously gemini-2.0-flash-001. Optimized for speed, this model provides fast text generation and efficient web search functionality with support for PDF, image, audio, and video inputs, but lacks complex reasoning capabilities. With a context window of 1 million tokens, it’s best suited for scenarios requiring quick, responsive interactions and moderate multimodal input handling. Now available on the Free plan.
gemini-2.0-flash-thinking-exp-01-21
A reasoning-focused, rapid-response model featuring advanced logical reasoning capabilities and multimodal support (PDF, images, audio, and video). This model does not include web search functionality but is optimized for tasks requiring analytical depth, critical thinking, and efficient multimodal reasoning within a context window of 1 million tokens. Available on the Free plan.
gemini-2.0-pro-exp-02-05
A balanced, professional-level model offering robust text generation and effective web search capabilities. Supports multiple inputs such as PDF, image, audio, and video but excludes advanced reasoning capabilities. With a context window of 1 million tokens, it is well-suited for general multimodal generation and standard use cases. Available on the Free plan.
Model Selection Guide
Guidelines for selecting the optimal model based on your needs and plan:
Free Plan Models:
- For experimenting with advanced features:
gemini-2.5-pro-exp-03-25(State-of-the-art, all features) - For advanced reasoning & logical analysis:
gemini-2.0-flash-thinking-exp-01-21(Fast reasoning) - For balanced general-purpose performance:
gemini-2.0-pro-exp-02-05(Good all-rounder, no reasoning) - For fast responses without complex reasoning:
gemini-2.0-flash(Speed priority)
Pro Plan Models:
- For best overall performance and complex tasks:
gemini-2.5-pro-preview-03-25(Most powerful, all features) - For fast responses with reasoning:
gemini-2.5-flash-preview-04-17(Speed + Reasoning balance)
Practices for Giselle
We recommend gemini-2.5-pro-preview-03-25 (Pro plan) as your primary model in Giselle due to its proven power and stability for complex tasks. For users seeking the absolute latest features on the Free plan, the gemini-2.5-pro-exp-03-25 model is also available and offers similar cutting-edge capabilities. Both are capable of processing large volumes of data, executing complex code reviews, and handling a wide variety of business tasks.
For users prioritizing speed, the gemini-2.0-flash model is now an excellent option on the Free plan. Pro users seeking a balance of speed and reasoning might consider the new gemini-2.5-flash-preview-04-17.
By enabling the Search grounding feature with these models (where applicable), you can access web search functionality, allowing you to supplement your workflows with the most current information available.
For detailed specifications, performance benchmarks, or additional assistance, please check Google AI for Developers.