google/gemini-3.1-flash-lite
リリース日: 2026-05-07
1,048,576 context · $0.25/M input tokens · $1.50/M output tokens
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, with a 1M-token context window and up to 64K output tokens. The model is designed for lightweight agentic workflows, simple data extraction, classification, summarization, document understanding, and responsive applications where API cost and speed are primary constraints. It supports thinking levels from minimal to high for fine-grained cost/performance control and is priced at half the cost of Gemini 3 Flash.
料金
従量課金
初期費用なし、使った分だけお支払い
モデルを試す
API 利用
以下のコード例を使用して API と連携してください:
import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'google/gemini-3.1-flash-lite',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}import OpenAI from 'openai';
if (!process.env.WAVESPEED_API_KEY) throw new Error('Set WAVESPEED_API_KEY');
const client = new OpenAI({
apiKey: process.env.WAVESPEED_API_KEY,
baseURL: 'https://llm.wavespeed.ai/v1',
timeout: 120_000,
maxRetries: 2,
});
try {
const response = await client.chat.completions.create({
model: 'google/gemini-3.1-flash-lite',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}モデル紹介
Google: Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, classification, summarization, and applications where responsiveness and API cost are the primary constraints.
Why It Looks Great
- High-efficiency multimodal model for text, image, video, audio, and PDF understanding
- Optimized for low-latency, high-volume production workloads
- Supports a 1M-token context window for long prompts, document analysis, and multi-turn workflows
- Up to 64K output tokens for extended responses and structured generation
- Thinking levels from minimal to high for cost, latency, and quality trade-offs
- Priced at half the cost of Gemini 3 Flash
- Strong fit for lightweight agents, simple extraction tasks, summarization, classification, and responsive app experiences
Key Features
- Context Window: 1,048,576 tokens
- Max Input: 983,040 tokens
- Max Output: 65,536 tokens
- Input: Text, Image, Video, Audio, PDF
- Output: Text
- Vision: Supported
- Audio Input: Supported
- Function Calling: Supported
- Structured Outputs: Supported
- Thinking Levels: minimal, low, medium, high
Specifications
| Specification | Value |
|---|---|
| Provider | |
| Model Type | Chat Completions model |
| Architecture | text+image+file+audio+video->text |
| Context Window | 1,048,576 tokens |
| Max Input | 983,040 tokens |
| Max Output | 65,536 tokens |
| Input | Text, Image, Video, Audio, PDF |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Structured Outputs | Supported |
| Audio Input | Supported |
| Thinking Levels | minimal, low, medium, high |
Pricing
| Token Type | Cost |
|---|---|
| Input | $0.25 per million tokens |
| Output | $1.50 per million tokens |
| Cached Input | $0.025 per million tokens |
| Cache Write | $0.083333 per million tokens |
| Reasoning Output | $1.50 per million tokens |
How to Use
API Integration
Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: google/gemini-3.1-flash-lite
情報
対応機能
API アクセスガイド
Gemini 3.1 Flash Lite API
google/gemini-3.1-flash-lite
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, with a 1M-token context window and up to 64K output tokens. The model is designed for lightweight agentic workflows, simple data extraction, classification, summarization, document understanding, and responsive applications where API cost and speed are primary constraints. It supports thinking levels from minimal to high for fine-grained cost/performance control and is priced at half the cost of Gemini 3 Flash.
入力
$0.25 /M
出力
$1.5 /M
コンテキスト
1049K
最大出力
66K
Vision
対応
ツール利用
対応
WaveSpeedAIでGemini 3.1 Flash Liteを試す
統合APIを通じてGemini 3.1 Flash Liteにアクセス — OpenAI互換、コールドスタートなし、透明な料金。
Gemini 3.1 Flash Liteに関するよくある質問
Gemini 3.1 Flash Lite API の料金はいくらですか?+
WaveSpeedAI の料金: 入力 100 万トークンあたり $0.25、出力 100 万トークンあたり $1.50。プロンプトキャッシュとバッチ処理は別途料金で、長く反復的なワークロードでは実効コストを下げられます。
Gemini 3.1 Flash Lite のコンテキストウィンドウはどのくらいですか?+
Gemini 3.1 Flash Lite はリクエストあたり最大 1049K のコンテキストトークンと最大 66K の出力トークンをサポートします。
Gemini 3.1 Flash Lite は OpenAI 互換ですか?+
WaveSpeedAI は https://llm.wavespeed.ai/v1 の OpenAI 互換 Chat Completions インターフェースで Gemini 3.1 Flash Lite を提供します。多くの OpenAI SDK クライアントはベース URL と API キーの変更で利用できますが、オプション項目はモデルごとに異なります。
Gemini 3.1 Flash Lite を使い始めるには?+
WaveSpeedAI にサインインし、Access Keys で API キーを作成して、上に表示されたモデル ID を指定して https://llm.wavespeed.ai/v1/chat/completions にリクエストを送信してください。提供状況、機能、料金は最新のモデルカタログで確認してください。