Gemini 3.7 Flash
$0.14780% offper 1M tokens$0.7580% off
A multimodal Flash model for fast agent workflows, coding, and multi-step reasoning, built for tasks that need responsive performance.
1.05MContext
$0.147Input / 1M
$0.735Output / 1M
80%Saved vs retail
client.chat.completions.create( model="gemini-3-7-flash", messages=[ {"role": "user", "content": "Hello"}, ],)
Cost per 1M input tokens
Studios$0.147
Retail$0.75