Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide

Short summary

Google's Gemini 3.6 Flash and 3.5 Flash-Lite are now GA with improved agentic performance, reduced token usage, and lower pricing. 3.6 Flash costs $1.50/$7.50 per 1M input/output tokens with better code generation and multimodal reasoning; Flash-Lite targets high-throughput at $0.30/$2.50. Migration is a single model ID change with no API friction.

• •Gemini 3.6 Flash GA with 17% fewer tokens and lower output cost vs 3.5 Flash
• •Flash-Lite offers 350 tokens/sec for high-throughput tasks at $0.30/$2.50 per 1M
• •Migration is a single parameter change; both support 1M context and Computer Use

Generated with AI, which can make mistakes.