Gemini 3 is available via API with updates for developers: new `thinking_level` for depth control, `media_resolution` for multimodal processing, and enforced `Thought Signatures` for agentic workflows, especially with function calling and image generation. It also introduces combining Google Search/URL Grounding with Structured Outputs and new usage-based pricing for Grounding. Best practices, like using default temperature, are advised for optimal results.
New Gemini API updates for Gemini 3
Related Posts
4 Ins and Outs of 2024: Vector Database Edition
If your recommendations are still similar in 2024, you’re doing it wrong (respectfully). Here’s a summary of what’s…
DRY, KISS, and YAGNI to avoid Over-engineering Trap
Refactor and architect your code based on DRY, KISS, and YAGNI principles, beware of over-engineering trap that leads…
DRF-YASG: The Superhero of API Documentation – Saving Developers from Documentation Despair!
In the midst of a migration project at my workplace, where we are transitioning a web application from…
