Added the Gemini 3.8 Flash model page (gemini-3.8-flash), documenting Google’s most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows, with 1,048,576 input / 65,536 output…
Changelog
Models
Added the Gemini 3.8 Flash model page (gemini-3.8-flash), documenting Google’s most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows, with 1,048,576 input / 65,536 output token limits and support for caching, code execution, computer use (preview), file search, function calling, grounding, structured outputs, thinking (low/medium/high), Batch API, and flex/priority inference.
Updated the changelog with the September 2, 2026 GA release of Gemini 3.8 Flash.
Updated the docs home (/gemini-api/docs), latest model, and related guides so examples and featured Flash model references use gemini-3.8-flash.
Agents
Updated Antigravity agent and agents docs: default model is now Gemini 3.8 Flash (gemini-3.8-flash); Gemini 3.7 Flash remains available as a prior-generation option via agent_config.
API features & guides
Documented Gemini 3.8 Flash on the caching page (minimum token limit 4,096).