Seedance 2.0 15 % RABATT | Im Video Generator erstellen →
google
google/gemini-3.1-pro-preview-customtools

google/gemini-3.1-pro-preview-customtools

Veröffentlichungsdatum: 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.

Preise

Pay-per-Use

Keine Vorabkosten, zahlen Sie nur, was Sie nutzen

Eingabe
200K $2.00 / M Tokens
> 200K $4.00 / M Tokens
Ausgabe
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

Modell ausprobieren

google/gemini-3.1-pro-preview-customtools
Online
google
Hallo! Ich bin ein hilfreicher KI-Assistent. Womit kann ich helfen?

API-Nutzung

Verwenden Sie die folgenden Codebeispiele zur Integration mit unserer 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)

Modelleinführung

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

Info

Anbietergoogle
Typllm

Unterstützte Funktionen

Eingabe
TextBildAudio
Ausgabe
Text
Kontext1,048,576
Max. Ausgabe65,536
Vision✓ Unterstützt
Function Calling✓ Unterstützt

API-Zugriffsanleitung

Base URLhttps://llm.wavespeed.ai/v1
API-Endpunktchat/completions
Modell-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.

Eingabe

$2 /M

Ausgabe

$12 /M

Kontext

1049K

Max. Ausgabe

66K

Vision

Unterstützt

Tool-Nutzung

Unterstützt

Gemini 3.1 Pro Preview Customtools auf WaveSpeedAI testen

Zugriff auf Gemini 3.1 Pro Preview Customtools über unsere einheitliche API — OpenAI-kompatibel, keine Kaltstarts, transparente Preise.

Häufige Fragen zu Gemini 3.1 Pro Preview Customtools

Wie viel kostet die Gemini 3.1 Pro Preview Customtools-API?+

Preise auf WaveSpeedAI: $2.00 pro Million Input-Tokens und $12.00 pro Million Output-Tokens. Prompt-Caching und Batch-Verarbeitung werden separat berechnet und reduzieren die effektiven Kosten bei langen, sich wiederholenden Workloads.

Wie groß ist das Kontextfenster von Gemini 3.1 Pro Preview Customtools?+

Gemini 3.1 Pro Preview Customtools unterstützt bis zu 1049K Kontext-Tokens und bis zu 66K Output-Tokens pro Anfrage.

Ist Gemini 3.1 Pro Preview Customtools OpenAI-kompatibel?+

Ja. WaveSpeedAI stellt Gemini 3.1 Pro Preview Customtools über einen OpenAI-kompatiblen Endpunkt unter https://llm.wavespeed.ai/v1 bereit. Richten Sie das offizielle OpenAI SDK mit Ihrem WaveSpeedAI-API-Schlüssel auf diese Base-URL — keine weiteren Codeänderungen erforderlich.

Wie starte ich mit Gemini 3.1 Pro Preview Customtools?+

Bei WaveSpeedAI anmelden, in Access Keys einen API-Schlüssel erstellen und eine Anfrage an https://llm.wavespeed.ai/v1/chat/completions mit der oben angezeigten Model-ID senden. Neue Konten erhalten kostenlose Credits, um Gemini 3.1 Pro Preview Customtools zu testen.

Verwandte LLM-APIs