In case you missed it in the title (or you don’t know what it means), this is mainly for when you access Gemini models through the API. That means if you use the Gemini app (gemini.google.com or the mobile app) these tips are not going to apply to you. Honestly, they might not even make sense.
Here are the things that Google recommends when migrating from Gemini 2.5 to Gemini 3
- Thinking: If you were previously using complex prompt engineering (like Chain-of-thought) to force Gemini 2.5 to reason, try Gemini 3 with thinking_level: "high" and simplified prompts.
- Temperature settings: If your existing code explicitly sets temperature (especially to low values for deterministic outputs), we recommend removing this parameter and using the Gemini 3 default of 1.0 to avoid potential looping issues or performance degradation on complex tasks.
- PDF & document understanding: Default OCR resolution for PDFs has changed. If you relied on specific behavior for dense document parsing, test the new media_resolution_high setting to ensure continued accuracy.
- Token consumption: Migrating to Gemini 3 Pro defaults may increase token usage for PDFs but decrease token usage for video. If requests now exceed the context window due to higher default resolutions, we recommend explicitly reducing the media resolution.
- Image segmentation: Image segmentation capabilities (returning pixel-level masks for objects) are not supported in Gemini 3 Pro. For workloads requiring native image segmentation, we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5.
In addition, these are some prompting best practices
- Precise instructions: Be concise in your input prompts. Gemini 3 responds best to direct, clear instructions. It may over-analyze verbose or overly complex prompt engineering techniques used for older models.
- Output verbosity: By default, Gemini 3 is less verbose and prefers providing direct, efficient answers. If your use case requires a more conversational or "chatty" persona, you must explicitly steer the model in the prompt (e.g., "Explain this as a friendly, talkative assistant").
- Context management: When working with large datasets (e.g., entire books, codebases, or long videos), place your specific instructions or questions at the end of the prompt, after the data context. Anchor the model's reasoning to the provided data by starting your question with a phrase like, "Based on the information above...".
Missed our video?
Watch here: