gemini-3.8-flash model and pricing

A fast Flash model for long-running software engineering, autonomous agents and enterprise workflows. Accepts text, images, video, audio and PDFs; produces text. Maximum input: 1,048,576 tokens; maximum output: 65,536. Thinking levels: low, medium, high; minimal is not supported. Supports function calling, structured output, code execution, file search, context caching and search grounding; image generation and the Live API are not supported.