Gemini 3.5 Flash
used in
0
stacks
Google's stable frontier model for sustained agentic and coding work, the current GA workhorse of the Gemini 3 family.
Gemini 3.5 Flash (model ID gemini-3.5-flash) is described by Google as its "most intelligent model for sustained frontier performance on agentic and coding tasks," and is generally available, stable, and ready for scaled production use. It has a 1M-token input context window and up to 65k output tokens, with selectable thinking levels (minimal, low, medium, high) and thought preservation across multi-turn conversations. Built-in tools include Function Calling, Google Search and Maps grounding, File Search, Code Execution, and URL Context. Other Gemini 3.x models (3.1 Pro, 3 Flash) remain in preview as of June 2026.
Strengths
- Only stable GA model in the Gemini 3.x family as of June 2026; positioned for agentic execution and sub-agent deployment
- 1M-token context window with thought preservation across multi-turn agent loops
- Rich built-in tool ecosystem (search/maps grounding, code execution, file search, function calling)
Tradeoffs
- Per Google docs: Computer Use is not supported at this moment (it was available in the Gemini 3 Flash Preview)
- Output capped at 65k tokens, lower than competing flagships' 128k