gemini-3.8-flash
Gemini 3.8 Flash is our most intelligent workhorse model yet, delivering significant improvements from 3.7 Flash across software engineering, agentic tasks, and critical, multi-step reasoning in specialized domains.
上下文
1M
输入 / 1M
$0.75
输出 / 1M
$3.75
Modalities
协议
1- generateContent
可用性与性能
近 7 天
正在加载模型性能
能力
文本推理视觉音频长上下文缓存
计费明细
输入 Tokens
$0.75/1M
输出 Tokens
$3.75/1M
缓存命中
$0.075/1M
缓存输入
$0.075/1M
cached_output
$0.075/1M
音频输入
$0.75/1M
音频输出
$3.75/1M
推理 Tokens
$3.75/1M
input_text
$0.75/1M
图片
$0.75/1M
output_text
$3.75/1M
output_image
$3.75/1M
input_above_threshold
$0.75/1M
cached_input_above_threshold
$0.075/1M
output_above_threshold
$3.75/1M
input_image_above_threshold
$0.75/1M
input_audio_above_threshold
$0.75/1M
价格以 USD / 1M tokens 展示（除非另注单位）。Batch API 与缓存命中会享有额外折扣，最终以工作空间实时费率为准。