Gemini 3.1 Pro Preview Custom Tools
VerifiedGoogle's multimodal preview model with custom tools and massive context handling.
About Gemini 3.1 Pro Preview Custom Tools
This preview model from Google combines a very large context capacity with support for multiple data types including text, audio, images, video, and files. It is not released as open weights and includes custom tool capabilities for flexible task execution. The architecture emphasizes handling lengthy multimodal inputs without requiring parameter counts to be disclosed.
Its primary strengths lie in managing complex, multi-format data streams within a single session thanks to the million-plus token window. Developers can leverage the custom tools feature to extend functionality for specialized workflows. As a closed model, it prioritizes controlled access and integration within Google's ecosystem.
Typical usage involves research, content analysis, and creative projects that require simultaneous processing of diverse media alongside long-form context. Users often apply it to scenarios needing precise tool-augmented reasoning across audio transcripts, visual data, and documents. The preview status indicates ongoing refinements for production reliability.
Capabilities
How Gemini 3.1 Pro Preview Custom Tools compares
Gemini 3.1 Pro Preview Custom Tools (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Gemini 3.1 Pro Preview Custom Tools ranks #89 of 122
Nova Premier 1.0Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long-Context Document Analysis
The 1,048,756-token context window allows processing of entire books, lengthy legal contracts, or full research papers in a single pass for summarization or insight extraction.
Multimodal Data Interpretation
As a multimodal model it handles combined text and image inputs to generate descriptions, answer questions about visuals, or create reports from charts and diagrams.
Custom Tool-Augmented Workflows
The preview version supports custom tool integration, enabling developers to build agents that call external functions or APIs while maintaining long conversation history.
Strengths & limitations
Strengths
- +Strong cross-modal coherence on mixed inputs
- +Effective use of very large context windows
- +Flexible extension via custom tools
Limitations
- –Preview status may include occasional instability
- –Large contexts can increase latency and cost
- –Tool setup requires additional configuration
Cost calculator
Estimate what Gemini 3.1 Pro Preview Custom Tools would cost for your usage.
Based on Gemini 3.1 Pro Preview Custom Tools's $2.00/1M input · $12.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "google/gemini-3.1-pro-preview-customtools",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: google/gemini-3.1-pro-preview-customtools
Editor's verdict
Gemini 3.1 Pro Preview Custom Tools is Google's proprietary multimodal with a 1049K-token context window.
At $12.00 per 1M output tokens, it is premium-priced for its class.
It is available through Google's API and aggregators like OpenRouter.
Best suited to strong cross-modal coherence on mixed inputs and effective use of very large context windows.
Frequently asked questions
The model provides a context length of 1,048,756 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Gemini models
Sibling versions in the Gemini family from Google.
Similar models
Other multimodal worth comparing.