Gemini 3.1 Flash Lite
Google 低延迟 Gemini 模型，面向高吞吐的多模态与智能体工作负载。
上下文窗口
1M tokens
gemini-3.1-flash-lite
最大输出
-
1M tokens
输入
$0.225$0.25
10% off1M tokens
输出
$0.675$0.75
10% off1M tokens
gemini-3.1-flash-lite试玩区
gemini-3.1-flash-liteClick or drag
暂无输出
定价
| 方案 | 上下文窗口 | 最大输出 | 输入 | 输出 | 缓存写入 | 缓存读取 |
|---|---|---|---|---|---|---|
gemini-3.1-flash-lite | 1M tokens | - | $0.225$0.2510% off 1M tokens | $0.675$0.7510% off 1M tokens | - | - |
Context caching · $0.01125 · 1M tokens
README
- Gemini 3.1 Flash Lite 支持思考（推理）：请求可能先花 token 推理再产出正文，max_tokens 应大于期望答案长度。
- 支持多模态输入（文本/图片/音频）与文本输出，具备工具调用与文件处理能力，上下文窗口 1M tokens。
- 作为低延迟模型，它面向高吞吐的多模态与智能体工作负载，适合更看重快速响应与成本效率、而非极限推理深度的场景。
API
API
端点
POST /v1beta/models/{model}:generateContent认证
x-goog-api-key: YOUR_REACH_API_KEY Content-Type: application/json
示例
curl -X POST "https://direct.reachapi.ai/v1beta/models/YOUR_MODEL_ID:generateContent" \
-H "x-goog-api-key: YOUR_REACH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Introduce ReachAPI in one sentence."
}
]
}
],
"generationConfig": {
"temperature": 0.2
}
}'相关模型
Gemini 4 Argon
Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents.
Gemini 3.8 Flash
Google's most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
Gemini 3.7 Flash
Google's high-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning.
Gemini 3.6 Flash
Google's fast Flash model balancing multimodal reasoning, tool use, and cost.
Gemini 3.1 Flash Image Preview
Google's high-efficiency preview image model for fast generation, conversational editing, and grounded visual workflows.
Gemini 3.1 Pro Preview
Google's preview model for the most complex reasoning and agentic workflows.