Enterprise DNAEnterprise DNA
Google logo

Models · Best coding

Gemini 3.1 Pro Preview

by Google

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage.

Visit Google ↗

Our verdict

Not reviewed yet

We have not reviewed Gemini 3.1 Pro Preview yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Gemini 3.1 Pro Preview

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.

Notes

Gemini 3.1 Pro Preview is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$2.00 per million tokens
Checked OpenRouter models API
Output price
$12.00 per million tokens
Checked OpenRouter models API
Price on google-ai-studio
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on google-ai-studio
$1.00 per million input tokens
Checked OpenRouter models API
Price on google-ai-studio
$6.00 per million output tokens
Checked OpenRouter models API
Price on google-vertex
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on google-vertex
$1.00 per million input tokens
Checked OpenRouter models API
Price on google-vertex
$6.00 per million output tokens
Checked OpenRouter models API
Latest preview version
google/gemini-3.1-pro-preview-20260219
Checked OpenRouter models API
Gpqa diamond
94.4% (for 19 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
59.6% (for 19 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Terminal bench
80.2% (for 19 Feb 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `google/gemini-3.1-pro-preview`.

  • openrouter · google/gemini-3.1-pro-preview · Docs

OpenRouter id: google/gemini-3.1-pro-preview

Price

What Gemini 3.1 Pro Preview costs, over time

Input price

$2.00 to $2.00

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$12.00 to $12.00

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
google-ai-studioCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-ai-studioInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-ai-studioOutput$6.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$1.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$6.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Gemini 3.1 Pro Preview is used

Tokens served a day

50.5B to 17.7B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Gemini 3.1 Pro Preview scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index29.7indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index68.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index8.2indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,480EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,446EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)1,296EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,279EloAs of 10 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)35.1percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)98percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)77.1percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Balrog (best-across-versions)57percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)51percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Show 24 more scores
ScoreValueSourceChecked
Cl bench (best-across-versions)20.8percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Cl bench life (best-across-versions)16.9percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Deepresearch bench (best-across-versions)47.8percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)97.1percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Ebr bench (best-across-versions)14.3percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Exploitbench (best-across-versions)26.1percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Frontiermath 2025 02 28 private (best-across-versions)36.9percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 2025 07 01 private (best-across-versions)16.7percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)26.8percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)59.6percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Furniture assembly (best-across-versions)26.7percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)94.4percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Gso bench (best-across-versions)22.6percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)53.8percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Metr time horizons (best-across-versions)77percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Mirrorcode (best-across-versions)8.9percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)34percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated95.6percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Posttrainbench (best-across-versions)22percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)26percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)79.6percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)73.5percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Terminal bench (best-across-versions)80.2percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)72.1percentAs of 19 Feb 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much Gemini 3.1 Pro Preview is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
88.1B ▼4%
Requests, last 7 days
8.1M
Tool calls, last 7 days
703K
People's vote
1480
Average cost per request
$3.87
Price per million tokens
$2 in · $12 out
050B100B19 Sept: 50.5B tokens, 3.2M requests20 Sept: 32.3B tokens, 1.7M requests21 Sept: 25.6B tokens, 2.1M requests22 Sept: 23.8B tokens, 1.8M requests23 Sept: 31.5B tokens, 2.5M requests24 Sept: 37.6B tokens, 2.4M requests25 Sept: 31.8B tokens, 3.4M requests26 Sept: 30.5B tokens, 3.6M requests27 Sept: 17.9B tokens, 1.3M requests28 Sept: 30.2B tokens, 3M requests29 Sept: 24.1B tokens, 1.8M requests30 Sept: 34.6B tokens, 2.6M requests1 Oct: 37.7B tokens, 4.7M requests2 Oct: 37.2B tokens, 4.6M requests3 Oct: 30.5B tokens, 2.8M requests4 Oct: 26.8B tokens, 2.5M requests5 Oct: 29.8B tokens, 2.5M requests6 Oct: 35.1B tokens, 2.9M requests7 Oct: 39.2B tokens, 2.8M requests8 Oct: 33B tokens, 2.8M requests9 Oct: 28.5B tokens, 2.1M requests10 Oct: 20.4B tokens, 1.4M requests11 Oct: 20B tokens, 1.3M requests12 Oct: 28.9B tokens, 2M requests13 Oct: 38.9B tokens, 2.9M requests14 Oct: 21.9B tokens, 1.9M requests15 Oct: 18.6B tokens, 1.6M requests16 Oct: 25.5B tokens, 2.7M requests17 Oct: 15.9B tokens, 4.8M requests18 Oct: 19.3B tokens, 1.4M requests19 Oct: 15.7B tokens, 1.1M requests20 Oct: 19.1B tokens, 1.4M requests21 Oct: 17B tokens, 1.5M requests22 Oct: 20.3B tokens, 1.7M requests23 Oct: 17.6B tokens, 2.1M requests24 Oct: 8.5B tokens, 1.8M requests25 Oct: 7.4B tokens, 1.7M requests26 Oct: 12.8B tokens, 962K requests27 Oct: 14.5B tokens, 1.2M requests28 Oct: 13.6B tokens, 1.1M requests29 Oct: 13.2B tokens, 1M requests30 Oct: 14.9B tokens, 1.2M requests31 Oct: 9.5B tokens, 691K requests1 Nov: 7.4B tokens, 712K requests2 Nov: 17.6B tokens, 1.4M requests3 Nov: 15.7B tokens, 1.4M requests4 Nov: 12.6B tokens, 1.5M requests5 Nov: 12.6B tokens, 1.4M requests6 Nov: 12.6B tokens, 984K requests7 Nov: 10.4B tokens, 733K requests8 Nov: 9.5B tokens, 878K requests9 Nov: 12.8B tokens, 1.2M requests10 Nov: 17.7B tokens, 1.5M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Gemini 3.1 Pro Preview.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperGoogle
Exact model identifiergoogle/gemini-3.1-pro-preview
Inputaudio, file, image, text, video
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
19 Feb 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

google/gemini-3.1-pro-preview: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 68.8 (2026-11-09) ↗Agentic Index: 8.2 (2026-11-09) ↗Design Arena: 1281 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →