---
id: "google/gemini-3.6-flash"
also: ["google/gemini-3.6-flash-20260721", "requesty/google/gemini-3.6-flash", "vercel/google/gemini-3.6-flash"]
cheapest_list_usd_per_m: "0.375 in, 1.875 out, at google-ai-studio/flex on openrouter"
cheapest_effective_usd_per_m: "0.3228 in, 1.8745 out, at google-vertex/global/flex on openrouter"
context: 1048576
max_output: 65536
input: ["text", "image", "video", "file", "audio"]
output: ["text"]
released: "2026-07-21"
reasoning: ["high", "medium", "low", "minimal"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 11
gateways: "openrouter (7), requesty (2), vercel (2)"
no_training: 10
trains: 0
retains_prompts: 3
coding: 69.2000
agentic: 29
---
# Google: Gemini 3.6 Flash

Gemini 3.6 Flash is the latest Flash model in the Gemini series, delivering frontier level intelligence at high speed and low cost. Built for the agentic era, it excels at sub agent deployment, multi step workflows, and long horizon tasks at scale.