Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Eden AI logo

Model details

Gemini 3.1 Pro Preview Custom Tools

Gemini 3.1 Pro Preview Custom Tools is a variant within the Gemini 3.1 Pro lineup that has been retuned for tool use inside agentic systems. Rather than broadening the base model's general capabilities, the variant focuses on function-calling reliability, pushing the model toward registered custom functions instead of a generic bash tool whenever a more specific registered tool fits the task. This makes it especially attractive for coding agents and multi-tool orchestrations where choosing the right tool on each step is more important than raw capability breadth, and it retains the multimodal understanding of the underlying Gemini 3.1 Pro family across text, images, video, audio, and documents.

In practice, the model accepts text, audio, image, video, and file inputs and produces text output, operating with a 1,048,576-token that quick-info value window and a maximum output on the order of the cataloged API limit tokens, which is well suited to long documents and multi-turn agent loops. Strengths highlighted by catalog evidence include reasoning, tool calling, and structured outputs, with the variant positioning itself as a good fit for image understanding, long-document analysis, structured response generation, and deep analysis scenarios that involve chaining tools. Because the core change is targeted steering of tool selection rather than a wholesale redesign, teams already invested in Gemini 3.1 Pro can adopt it as a drop-in option for agentic pipelines that need more consistent and predictable function-calling behavior.

Eden AIgoogle/gemini-3.1-pro-preview-customtoolsgemini-pro

Quick Info

Powered by
Provider
Eden AI
Model key
google/gemini-3.1-pro-preview-customtools
Release date
Feb 19, 2026
Last updated
Feb 19, 2026
Knowledge cutoff
2025-01
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$2.00
Output token cost
$12.00

Limits

Output tokens
65,536 tokens
Context window
1,048,576 tokens

Transparent token rates

Compare Gemini 3.1 Pro Preview Custom Tools pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Gemini 3.1 Pro Preview Custom Tools

Eden AI

CoverageBenchmark

Gemini 3.1 Pro Preview Custom Tools is cataloged by Google as a variant of Gemini 3.1 Pro released around late February 2026, with LM Market Cap dating the entry to February 25, 2026, and describing it as a build that improves tool selection by steering the model away from overusing a general-purpose bash tool in favor On LM Market Cap's composite scorecard the variant earns an overall 92, placing it 14th of 404 models in the Coding category (top 3%), with benchmark performance citing an LMSYS Arena Elo of 1494, Vision Elo of 1278, and 99th-percentile standing; signal breakdown weights benchmarks at 30%, capabilities at 20%, recency

Eden AI

CoverageBenchmark

The LM Market Cap profile for Gemini 3.1 Pro Preview describes it as Google's frontier reasoning model with enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. The 3.1 update is credited with measurable gains in SWE benchmarks and real-world The page records API pricing at $2/M input and $12/M output, a 1.0M context window with 65.5K max output, a release date of 2026-02-19, and an overall score of 92, ranking 15 of 404 in the Coding category. Signal breakdown gives benchmarks 92 (30% weight), capabilities 100 (20%), recency 97 (15%), pricing 88 (15%), con

Eden AI

CoverageBenchmark

Opper's catalog page, published August 27, 2026, explicitly names Gemini 3.1 Pro Preview Custom Tools and frames it as a specialized variant of Gemini 3.1 Pro that improves tool use in complex agentic workflows by increasing function-calling reliability and steering the model toward registered custom functions instead Key info on the Opper listing shows input pricing at $2.00 per million tokens and output at $12.00 per million tokens, with reasoning, tools, structured output, and PDF input features; a single route runs the model via Google Cloud in the US with no training on customer data by default, GDPR DPA available, and 99.00% r

Eden AI

CoveragePreview

Models.dev catalogs google/gemini-3.1-pro-preview-customtools as an advanced Gemini-family model released and last updated on 2026-02-19, with a knowledge cutoff of 2025-01, closed weights, and a 1,048,576-token context window capped at 65,536 output tokens; it lists Eden AI among ten providers hosting the model under The page frames the variant as aimed at complex reasoning, coding, and multimodal analysis tasks, while the Eden AI entry specifically uses the model ID google/gemini-3.1-pro-preview-customtools with matching context, output, and pricing columns. Provider labels attribute the model lab to Google and the family to gemin

Videos about Gemini 3.1 Pro Preview Custom Tools

More models around Gemini 3.1 Pro Preview Custom Tools