Google: Gemini 3.1 Pro Preview Custom Tools

File input Image input Audio input Text input Video input Text output
Author's Description

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.

Key Specifications
Cost
$$$$$
Context
1M
Released
Feb 25, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Response Format Structured Outputs Temperature Top P Tool Choice Max Tokens Seed Stop Reasoning Include Reasoning
Features

This model supports the following features:

Reasoning Structured Outputs Tools Response Format
Performance Summary

Google's Gemini 3.1 Pro Preview Custom Tools demonstrates exceptional reliability, achieving a 100% success rate across all benchmarks, indicating consistent and stable operation. While its speed performance is moderate, ranking in the 22nd percentile, its pricing tends to be at premium levels, positioned in the 5th percentile. This specialized variant excels in improving tool selection behavior, particularly in complex multi-tool workflows and coding agents, by prioritizing efficient third-party or user-defined functions over general bash tools. The model exhibits outstanding accuracy in critical areas such as Hallucinations (100%), Reasoning (100%), and Ethics (100%), often achieving perfect scores and being the most accurate at its price point and speed. It also shows strong performance in Instruction Following (94.9%), Coding (96.9%), and Mathematics (95.9%), placing it in the top percentiles for these categories. Its General Knowledge (99.5%) is robust, though its Email Classification (97.0%) is more moderate. The core strengths lie in its multimodal reasoning, 1M-token context window, and enhanced function calling reliability, making it highly suitable for sophisticated software engineering tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2
Completion $12
Input Cache Read $0.2
Input Cache Write $0.375
Internal Reasoning $12

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Google AI Studio
Google AI Studio | google/gemini-3.1-pro-preview-customtools-20260219 1M $2 / 1M tokens $12 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google