google/gemini-3.5-flash
출시일: 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.
가격
사용량 기반 과금
선결제 없이 사용한 만큼만 지불
모델 사용해 보기
API 사용법
다음 코드 예시를 사용해 API와 연동하세요:
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;
}모델 소개
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!"}]
}'정보
지원 기능
API 접근 가이드
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.
입력
$1.5 /M
출력
$9 /M
컨텍스트
1049K
최대 출력
66K
Vision
지원
도구 사용
지원
WaveSpeedAI에서 Gemini 3.5 Flash 체험
통합 API를 통해 Gemini 3.5 Flash 액세스 — OpenAI 호환, 콜드 스타트 없음, 투명한 가격.
Gemini 3.5 Flash에 대해 자주 묻는 질문
Gemini 3.5 Flash API 비용은 얼마인가요?+
WaveSpeedAI 가격: 입력 토큰 100만 개당 $1.50, 출력 토큰 100만 개당 $9.00. 프롬프트 캐싱과 배치 처리는 별도로 청구되며 긴 반복 작업에서 실질 비용을 줄여 줍니다.
Gemini 3.5 Flash의 컨텍스트 윈도우는 얼마나 되나요?+
Gemini 3.5 Flash은 요청당 최대 1049K 컨텍스트 토큰과 최대 66K 출력 토큰을 지원합니다.
Gemini 3.5 Flash은 OpenAI 호환인가요?+
WaveSpeedAI는 https://llm.wavespeed.ai/v1의 OpenAI 호환 Chat Completions 인터페이스를 통해 Gemini 3.5 Flash을 제공합니다. 대부분의 OpenAI SDK 클라이언트는 base URL과 API 키를 변경해 사용할 수 있으며, 선택 필드는 모델에 따라 다릅니다.
Gemini 3.5 Flash을 어떻게 시작하나요?+
WaveSpeedAI에 로그인하고 Access Keys에서 API 키를 만든 다음, 위에 표시된 모델 ID로 https://llm.wavespeed.ai/v1/chat/completions에 요청을 보내세요. 제공 여부, 기능 및 가격은 최신 모델 카탈로그를 확인하세요.