Model identifier: gemini-3.8-flash.
Google multimodal model for software engineering, autonomous agents and enterprise workflows.
Input limit: 1,048,576 tokens; output limit: 65,536. Standard paid rates per million tokens are $0.75 input and $3.75 output through December 31, 2026; $1.50 and $7.50 from January 1, 2027. A limited free API tier is documented. Stable; available through Gemini API and Google AI Studio. Output pricing includes thinking tokens. Tool, caching and alternate service-tier charges are separate. Pricing: https://ai.google.dev/gemini-api/docs/pricing . API access terms: https://ai.google.dev/gemini-api/terms
Official model documentation: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash Researched on 23 October 2026. Undocumented specifications are omitted.