Seedance 2.0 15% 할인 | Video Generator에서 만들기 →
google
google/gemini-3.1-pro-preview-customtools

google/gemini-3.1-pro-preview-customtools

출시일: 2026-02-26

1,048,576 context · $2.00/M input tokens · $12.00/M output tokens

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows. It retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.

가격

사용량 기반 과금

선결제 없이 사용한 만큼만 지불

입력
200K $2.00 / M Tokens
> 200K $4.00 / M Tokens
출력
200K $12.00 / M Tokens
> 200K $18.00 / M Tokens
Cache Read
200K $0.20 / M Tokens
> 200K $0.40 / M Tokens
Cache Write$0.38 / M Tokens

모델 사용해 보기

google/gemini-3.1-pro-preview-customtools
온라인
google
안녕하세요! 도움이 되는 AI 어시스턴트입니다. 무엇을 도와드릴까요?

API 사용법

다음 코드 예시를 사용해 API와 연동하세요:

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-3.1-pro-preview-customtools",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

모델 소개

Google gemini-3.1-pro-preview-customtools

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows. It retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 1048576 context window for long document handling
  • Competitive pricing at $2.0/$12.0 per million tokens

Key Features

  • Context Window: 1048576 tokens
  • Max Output: 65536 tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderGoogle
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window1048576 tokens
Max Output65536 tokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$2.0
Output$12.0

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. 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-3.1-pro-preview-customtools


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-3.1-pro-preview-customtools",
    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-3.1-pro-preview-customtools",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: google/gemini-3.1-pro-preview-customtools
  • Provider: Google

정보

제공자google
유형llm

지원 기능

입력
텍스트이미지오디오
출력
텍스트
컨텍스트1,048,576
최대 출력65,536
Vision✓ 지원
Function Calling✓ 지원

API 접근 가이드

Base URLhttps://llm.wavespeed.ai/v1
API 엔드포인트chat/completions
모델 IDgoogle/gemini-3.1-pro-preview-customtools

Gemini 3.1 Pro Preview Customtools API

google/gemini-3.1-pro-preview-customtools

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party or user-defined functions are available. This specialized preview endpoint significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows. It retains the core strengths of Gemini 3.1 Pro, including multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance.

입력

$2 /M

출력

$12 /M

컨텍스트

1049K

최대 출력

66K

Vision

지원

도구 사용

지원

WaveSpeedAI에서 Gemini 3.1 Pro Preview Customtools 체험

통합 API를 통해 Gemini 3.1 Pro Preview Customtools 액세스 — OpenAI 호환, 콜드 스타트 없음, 투명한 가격.

Gemini 3.1 Pro Preview Customtools에 대해 자주 묻는 질문

Gemini 3.1 Pro Preview Customtools API 비용은 얼마인가요?+

WaveSpeedAI 가격: 입력 토큰 100만 개당 $2.00, 출력 토큰 100만 개당 $12.00. 프롬프트 캐싱과 배치 처리는 별도로 청구되며 긴 반복 작업에서 실질 비용을 줄여 줍니다.

Gemini 3.1 Pro Preview Customtools의 컨텍스트 윈도우는 얼마나 되나요?+

Gemini 3.1 Pro Preview Customtools은 요청당 최대 1049K 컨텍스트 토큰과 최대 66K 출력 토큰을 지원합니다.

Gemini 3.1 Pro Preview Customtools은 OpenAI 호환인가요?+

네. WaveSpeedAI는 OpenAI 호환 엔드포인트 https://llm.wavespeed.ai/v1을 통해 Gemini 3.1 Pro Preview Customtools을 제공합니다. 공식 OpenAI SDK의 base URL을 이 주소로 변경하고 WaveSpeedAI API 키를 사용하면 코드 변경 없이 사용할 수 있습니다.

Gemini 3.1 Pro Preview Customtools을 어떻게 시작하나요?+

WaveSpeedAI에 로그인하고 Access Keys에서 API 키를 만든 다음, 위에 표시된 모델 ID로 https://llm.wavespeed.ai/v1/chat/completions에 요청을 보내세요. 신규 계정은 Gemini 3.1 Pro Preview Customtools을 평가할 수 있는 무료 크레딧을 받습니다.

관련 LLM API