The original title is "Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide"

Short summary

Google announced GA availability of Gemini 3.6 Flash ($1.50/$7.50 per 1M input/output tokens) and Gemini 3.5 Flash-Lite ($0.30/$2.50 per 1M), both supporting 1M token context, 64k output, thinking, and Computer Use. The 3.6 Flash improves agentic task performance, code generation quality, and instruction following while reducing token usage and cost versus 3.5 Flash. Flash-Lite offers the highest throughput in the 3.5 family with improved reasoning and multimodal benchmarks over prior generations. The guide includes API code samples and migration instructions.

• •Gemini 3.6 Flash GA at $1.50/$7.50 per 1M tokens — improved agentic tasks, code gen, multimodal reasoning vs 3.5 Flash
• •Gemini 3.5 Flash-Lite GA at $0.30/$2.50 per 1M tokens — fastest, lowest-cost 3.5 model for high-throughput workloads
• •Both support 1M context, 64k output, thinking levels, and Computer Use; migration guide with code samples included

Generated with AI, which can make mistakes.