Seedance 2.0 立省 15% | 在 Video Generator 中创作 →
google
google/gemini-3.1-pro-preview-customtools

google/gemini-3.1-pro-preview-customtools

发布时间: 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.

定价

按量付费

无需预付费用,仅按实际使用量付费

输入
200K $2.00 / M Tokens
> 200K $4.00 / M Tokens
输出
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

试用模型

google/gemini-3.1-pro-preview-customtools
在线
google
你好!我是乐于助人的 AI 助手。需要我帮你做什么?

API 使用

使用以下代码示例接入我们的 API:

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)

模型介绍

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

信息

提供商google
类型llm

支持功能

输入
文本图像音频
输出
文本
上下文1,048,576
最大输出65,536
视觉✓ 支持
函数调用✓ 支持

API 访问指南

Base URLhttps://llm.wavespeed.ai/v1
API 端点chat/completions
Model 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.

输入

$2 /M

输出

$12 /M

上下文

1049K

最大输出

66K

Vision

支持

工具调用

支持

在 WaveSpeedAI 试用 Gemini 3.1 Pro Preview Customtools

通过我们的统一 API 接入 Gemini 3.1 Pro Preview Customtools — 兼容 OpenAI、无冷启动、透明计费。

关于 Gemini 3.1 Pro Preview Customtools 的常见问题

Gemini 3.1 Pro Preview Customtools API 多少钱?+

WaveSpeedAI 定价:输入每百万 token $2.00,输出每百万 token $12.00。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。

Gemini 3.1 Pro Preview Customtools 的上下文窗口是多大?+

Gemini 3.1 Pro Preview Customtools 单次请求最多支持 1049K 上下文 token,输出最多 66K token。

Gemini 3.1 Pro Preview Customtools 是否兼容 OpenAI?+

是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 Gemini 3.1 Pro Preview Customtools。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。

如何开始使用 Gemini 3.1 Pro Preview Customtools?+

登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 Gemini 3.1 Pro Preview Customtools。

相关 LLM API