google/gemini-3.5-flash
發布時間: 2026-05-19
1,048,576 context · $1.50/M input tokens · $9.00/M output tokens
Gemini 3.5 Flash is Google’s high-efficiency multimodal model, delivering near-Pro-level reasoning and coding capabilities with Flash-class speed and cost efficiency. It is purpose-built for advanced coding workflows and parallel agentic execution, while supporting a wide range of input modalities including text, images, video, audio, and PDFs.
The model defaults to a medium reasoning mode to balance latency, quality, and cost, while also offering configurable thinking levels — minimal, low, medium, and high — for more precise performance and efficiency tuning across different workloads.
定價
按用量付費
無需預付費用，僅按實際使用量付費
試用模型
API 使用
使用以下程式碼範例整合我們的 API：
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-3.5-flash',
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-3.5-flash',
messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0]?.message?.content ?? '');
} catch (error) {
console.error('LLM request failed:', error);
process.exitCode = 1;
}模型介紹
Google: Gemini 3.5 Flash
Gemini 3.5 Flash is Google’s high-efficiency multimodal model, delivering near-Pro-level reasoning and coding capabilities with Flash-class speed and cost efficiency. It is purpose-built for advanced coding workflows and parallel agentic execution, while supporting a wide range of input modalities including text, images, video, audio, and PDFs.
The model defaults to a medium reasoning mode to balance latency, quality, and cost, while also offering configurable thinking levels — minimal, low, medium, and high — for more precise performance and efficiency tuning across different workloads.
Why It Looks Great
- text+image+file+audio+video->text architecture for Text, Image, Video, file, Audio to Text workloads
- 1048576 context window for long prompts, document analysis, and multi-turn workflows
- Competitive pricing at $1.5/$9 per million tokens
- Vision input support for image understanding and multimodal tasks
- Function calling and tool-use support for agentic application workflows
- Structured output support for JSON responses and schema-constrained generation
Key Features
- Context Window: 1048576 tokens
- Max Input: 983040 tokens
- Max Output: 65536 tokens
- Vision: Supported
- Function Calling: Supported
- Structured Outputs: Supported
- Image Generation: Not listed
- Audio Input: Supported
- Supported Parameters: include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
Specifications
| Specification | Value |
|---|---|
| Provider | |
| Model Type | Chat Completions model |
| Architecture | text+image+file+audio+video->text |
| Context Window | 1048576 tokens |
| Max Input | 983040 tokens |
| Max Output | 65536 tokens |
| Input | Text, Image, Video, file, Audio |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Structured Outputs | Supported |
How to Use
- Write your prompt - describe the task, provide context, and specify the desired output format.
- Submit - the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: google/gemini-3.5-flash
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="google/gemini-3.5-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "google/gemini-3.5-flash",
"messages": [{"role": "user", "content": "Hello!"}]
}'資訊
支援功能
API 存取指南
Gemini 3.5 Flash API
google/gemini-3.5-flash
Gemini 3.5 Flash is Google’s high-efficiency multimodal model, delivering near-Pro-level reasoning and coding capabilities with Flash-class speed and cost efficiency. It is purpose-built for advanced coding workflows and parallel agentic execution, while supporting a wide range of input modalities including text, images, video, audio, and PDFs. The model defaults to a medium reasoning mode to balance latency, quality, and cost, while also offering configurable thinking levels — minimal, low, medium, and high — for more precise performance and efficiency tuning across different workloads.
輸入
$1.5 /M
輸出
$9 /M
上下文
1049K
最大輸出
66K
Vision
支援
工具調用
支援
在 WaveSpeedAI 試用 Gemini 3.5 Flash
透過我們的統一 API 接入 Gemini 3.5 Flash — 相容 OpenAI、無冷啟動、透明計費。
關於 Gemini 3.5 Flash 的常見問題
Gemini 3.5 Flash API 多少錢?+
WaveSpeedAI 定價:輸入每百萬 token $1.50,輸出每百萬 token $9.00。Prompt 快取與批次處理分別計費,可顯著降低長上下文、高重複任務的實際成本。
Gemini 3.5 Flash 的上下文視窗有多大?+
Gemini 3.5 Flash 每次請求最多支援 1049K 上下文 token,輸出最多 66K token。
Gemini 3.5 Flash 是否相容 OpenAI?+
WaveSpeedAI 透過 https://llm.wavespeed.ai/v1 的 OpenAI 相容 Chat Completions 介面提供 Gemini 3.5 Flash。大多數 OpenAI SDK 用戶端只需更換 base URL 和 API Key；選用欄位取決於具體模型。
如何開始使用 Gemini 3.5 Flash?+
登入 WaveSpeedAI，在 Access Keys 中建立 API Key，然後使用上方顯示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 發送請求。模型可用性、能力和價格請以目前模型目錄為準。