Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Language Model

Google: Gemini 3.1 Pro Preview Custom ToolsTools First Reasoning

Try Google: Gemini 3.1 Pro Preview Custom ToolsAPI Documentation

Build Agentic Workflows

Tool Priority

Custom Tools Optimized

Prioritizes registered custom tools over bash in agentic flows.

Multimodal Input

1M Token Context

Handles text, images, video, audio with 1,048,576 token window.

Reasoning Enabled

Step-by-Step Thinking

Supports code execution, function calling, structured outputs.

Examples

See what Google: Gemini 3.1 Pro Preview Custom Tools can create

Copy any prompt below and try it yourself in the playground.

Code Search

“Find all Python files containing 'TODO' in the project directory. List file paths and line numbers with context.”

File Analysis

“Analyze this uploaded PDF schematic. Identify components, map connections, flag missing dependencies.”

Data Query

“Search codebase for functions using 'search_code' tool. Summarize usage patterns and suggest optimizations.”

Multimodal Task

“View this image of a circuit board. Extract handwritten notes, simulate 3D model, generate interactive code preview.”

For Developers

A few lines of code.
Tools. One call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per token, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/llm/chat/completions",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "",
  "model_id": ""
}
)
print(response.json())

FAQ

Common questions about Google: Gemini 3.1 Pro Preview Custom Tools

Read the docs

Specialized variant of Gemini 3.1 Pro released February 19, 2026. Optimizes for agentic workflows by prioritizing custom tools over bash commands. Model ID: gemini-3.1-pro-preview-customtools.

Prioritizes user-defined tools like view_file or search_code. Quality may fluctuate without tools. Same pricing as Gemini 3.1 Pro.

Supports 1,048,576 tokens input, 65,536 tokens output. Multimodal: text, image, video, audio, PDF.

Yes, excels in tool calling, reasoning, code execution. Use for multi-step tasks and custom integrations.

Available via Gemini API endpoint generativelanguage.googleapis.com. Integrates with OpenAI-compatible clients on platforms like OpenRouter.

Yes, caching supported at $0.2 per 1M tokens read. Pricing: $2 input, $12 output per 1M tokens.

Ready to create?

Start generating with Google: Gemini 3.1 Pro Preview Custom Tools on ModelsLab.

Try Google: Gemini 3.1 Pro Preview Custom ToolsAPI Documentation