提示：您可以使用支持技能的编码代理自动执行此迁移：https://ai.google.dev/gemini-api/docs/coding-agents#gemini-interactions-api（如 Antigravity）。运行 /gemini-interactions-api migrate my app to Gemini 3.6 Flash
Gemini 3.6 Flash ( gemini-3.6-flash ) and Gemini 3.5 Flash-Lite ( gemini-3.5-flash-lite ) are generally available (GA) and ready for production use.
This guide explains what's new in each model, what API changes affect your code, and how to migrate.
Tip : You can automate this migration with a coding agent that supports skills：https://ai.google.dev/gemini-api/docs/coding-agents#gemini-interactions-api (like Antigravity). Run /gemini-interactions-api migrate my app to Gemini 3.6 Flash
Both models support the 1M token context window, 64k max output tokens, thinking, and the full suite of built-in tools including Computer Use：https://ai.google.dev/gemini-api/docs/computer-use.
For complete specs, see the model pages:
For detailed pricing, see the pricing page：https://ai.google.dev/gemini-api/docs/pricing.
Use this table to select the right model and migration path for your workloads.
Both models require removing deprecated sampling parameters ( temperature , top_p , top_k ) and prefilled model turns. See API changes：#api-changes-and-parameter-updates for details.
Due to its improved performance, Gemini 3.6 Flash is now the new default model powering the Antigravity agent：https://ai.google.dev/gemini-api/docs/antigravity-agent in Gemini Managed Agents. This can be changed by setting a new field on the API.
Starting with Gemini 3.6 Flash and Gemini 3.5 Flash-Lite, the following API changes apply to these models and all future Gemini model releases.
Below are detailed explanations and code samples for each API change.
temperature , top_p , and top_k are deprecated and ignored. In future model generations, supplying these parameters returns an HTTP 400 error. Remove these parameters from all requests.
To improve determinism, define a system instruction with explicit rules for your specific use case.
API requests ending with a non-empty model role turn are disallowed and return an HTTP 400 Error .
In legacy generateContent or raw REST payloads, ending with a model role turn is now disallowed:
In the Interactions API, model turns are not manually prefilled. If your application previously prefilled a model turn to suppress preambles or force JSON formatting, use system_instruction or Structured outputs：https://ai.google.dev/gemini-api/docs/structured-output instead.
Templates let you quickly answer FAQs or store snippets for re-use.
Gemini has been getting stronger and stronger since version 3.1.
From my experience, it's even faster after version 3.5. Gemini has good programming capabilities and a beautiful UI.
Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink：#.
For further actions, you may consider blocking this person and/or reporting abuse：/report-abuse
Google AI Studio is the fastest way to start building with Gemini. Ready to build?
Thank you to our Diamond Sponsors for supporting the DEV Community
Google AI is the official AI Model and Platform Partner of DEV
Neon is the official database partner of DEV
Algolia is the official search partner of DEV
DEV Community：/ — A space to discuss and keep up software development and manage your software career
Built on Forem：https://www.forem.com — the open source：https://dev.to/t/opensource software that powers DEV：https://dev.to and other inclusive communities.
扫码直达文章详情