Can I run Gemini 3.1 Pro Preview locally?

No — Google has not released open weights for this model, so it is API access only.

What does Gemini 3.1 Pro Preview cost and how large is its context?

It costs $2.00 per million input tokens and $12.00 per million output tokens, with a context window of 1,048,576 tokens.

How does Gemini 3.1 Pro Preview differ from the base Gemini 3 Pro?

The 3.1 update adds measurable gains on SWE benchmarks, stronger agentic reliability in structured domains like finance and spreadsheets, improved token efficiency, and a new medium thinking level that lets you balance cost against reasoning depth.

▲

2.3%

this week

Gemini 3.1 Pro Preview

8206°

#llm #google #vision #audio #video #reasoning

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Google | 1,048,576 token context | $2.00/M input, $12.00/M output. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here:…Google | 1,048,576 token context | $2.00/M input, $12.00/M output. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoningOpens in new tab. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows. Designed for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.

Guides for this model

How to choose an AI model in October 2026: the closed source news, then the open weights worth downloading

Open weights vs open source vs API-only: what you are actually allowed to do

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Gemini 3.1 Pro Preview is Google's frontier reasoning model with a one-million-token context window and full multimodal capability across text, image, video, audio, and code. The 3.1 update sharpens software engineering performance, adds a medium thinking tier to balance cost against depth, and tightens tool orchestration for long-running agentic tasks. It suits developers and teams building autonomous agents, financial workflows, or anything that demands sustained reasoning over large, mixed-media inputs.

Known for

Measurable SWE benchmark gains and strong real-world coding performance
One-million-token context for large codebases, documents, or multi-turn workflows
Reliable tool orchestration across long-horizon agentic tasks
Multimodal input: text, image, video, audio, and code in one model
New medium thinking level to trade off cost, speed, and reasoning depth

Watch out for

Closed weights only — no local deployment, no self-hosting.
Output costs $12 per million tokens; reasoning-heavy agentic runs can add up fast.
Multi-turn tool calling requires preserving Reasoning Details or the chain breaks.

Best for

Prompts to try

Agentic code review plan

You are reviewing a Python microservice that handles payment webhooks. Outline a step-by-step plan to audit it for security issues, then write the first two audit functions: one that checks for missing HMAC signature validation and one that flags any raw SQL string concatenation. Explain each function's logic as you go.

Spreadsheet automation script

Write a Python script using openpyxl that reads a workbook called sales_data.xlsx, finds every sheet whose name starts with 'Q', sums the values in column C for rows where column A is not empty, and writes a summary sheet listing each quarter name and its total. Include error handling for missing columns.

Long-document reasoning

I am pasting a lengthy financial report below. Identify the three biggest risk factors the company discloses, explain how each one could affect free cash flow over the next two years, and flag any internal contradictions between the risk section and the forward guidance. Be specific about page references if they appear in the text.

Compare with

Gemma 4 31B
Open-weights model
262,144 token context · $0.20/M input, $0.40/M output
Gemma 4 26B A4B
Open-weights model
262,144 token context · $0.09/M input, $0.30/M output
gemma 4 31B it turbo
Open-weights model
262,144 token context · $0.09/M input, $0.34/M output
Gemini 3.8 Flash
API-only model
1,048,576 token context · $0.83/M input, $4.12/M output

More text models from google

Questions people ask

Can I run Gemini 3.1 Pro Preview locally?: No — Google has not released open weights for this model, so it is API access only.
What does Gemini 3.1 Pro Preview cost and how large is its context?: It costs $2.00 per million input tokens and $12.00 per million output tokens, with a context window of 1,048,576 tokens.
How does Gemini 3.1 Pro Preview differ from the base Gemini 3 Pro?: The 3.1 update adds measurable gains on SWE benchmarks, stronger agentic reliability in structured domains like finance and spreadsheets, improved token efficiency, and a new medium thinking level that lets you balance cost against reasoning depth.

Captain's verdict
A serious agentic and coding model — the million-token window and improved tool orchestration are real, but watch your output bill.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #67 Hottest Text / LLM model · #67 Hottest Text / LLM text model

Not this creator?

Get your own badge

Gemini 3.1 Pro Preview Popularity Trend

Heat score since 19 Feb 2026

Heat score

8,206°

This week

▲

2.3%

8,202° then, 8,206° now

This month

▲

11.1%

8,189° then, 8,206° now

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,206°

OpenRouter tokens

104,717,102,519 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 10,471 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,206°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
10,471 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,206°
8,206°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,206°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Similar Models

AI Models for Image, Video & Text Generation

Gemini 3.1 Pro Preview is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm google vision audio video reasoning coding agents

Browse by Model Family