Gemini 3.1 Pro Preview

Google · On OpenRouter since February 19, 2026 · Pinned version id: google/gemini-3.1-pro-preview-20260219

Price

$4.50

mixed / 1M tokens

Mixed price per 1M tokens: 3 input tokens to 1 output token.

in $2.00 · out $12.00 · Cached input $0.20

Price by prompt size

Price rises above 200k tokens

Up to 200k
$2.00 / $12.00
Above 200k
$4.00 / $18.00

Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.

US dollars per million tokens, converted to your currency at the NBP rate.

Tasks, with the evidence

Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.

Writing code Top 25%

Measured by a third party

Coding Index: 68.8 · Rank 16 of 86, among scored models · Top 25% · Artificial Analysis, read November 18, 2026

Code: 1,226 · Rank 50 of 122, among scored models · Design Arena, read November 21, 2026

Cost of this job: $1.65

Models that score at least as high for less in this scenario: 8

Agents that use tools

Measured by a third party

Agentic Index: 8.2 · Rank 39 of 64, among scored models · Artificial Analysis, read November 18, 2026

Cost of this job: $11.91

Models that score at least as high for less in this scenario: 28

Websites and apps

Measured by a third party

Websites: 1,240 · Rank 49 of 127, among scored models · Design Arena, read November 21, 2026

UI components: 1,264 · Rank 35 of 118, among scored models · Design Arena, read November 21, 2026

Web apps (agent): 1,097 · Rank 35 of 47, among scored models · Design Arena, read November 21, 2026

Full-stack apps (agent): 1,041 · Rank 34 of 45, among scored models · Design Arena, read November 21, 2026

Mobile apps (agent): 1,084 · Rank 43 of 50, among scored models · Design Arena, read November 21, 2026

Android apps (agent): 1,034 · Rank 38 of 41, among scored models · Design Arena, read November 21, 2026

Cost of this job: $1.11

Models that score at least as high for less in this scenario: 35

Games and 3D

Measured by a third party

Game development: 1,181 · Rank 59 of 121, among scored models · Design Arena, read November 21, 2026

3D scenes: 1,202 · Rank 46 of 114, among scored models · Design Arena, read November 21, 2026

Godot games (agent): 1,129 · Rank 23 of 34, among scored models · Design Arena, read November 21, 2026

Games (agent): 1,061 · Rank 23 of 25, among scored models · Design Arena, read November 21, 2026

Blender 3D (agent): 1,037 · Rank 17 of 25, among scored models · Design Arena, read November 21, 2026

Cost of this job: $1.11

Models that score at least as high for less in this scenario: 42

Slides and spreadsheets

Measured by a third party

PowerPoint files (agent): 1,109 · Rank 24 of 29, among scored models · Design Arena, read November 21, 2026

HTML slides (agent): 1,054 · Rank 18 of 25, among scored models · Design Arena, read November 21, 2026

Spreadsheets (agent): 918 · Rank 32 of 32, among scored models · Design Arena, read November 21, 2026

Cost of this job: $1.11

Models that score at least as high for less in this scenario: 16

Charts and graphics

Measured by a third party

Data visualization: 1,233 · Rank 42 of 112, among scored models · Design Arena, read November 21, 2026

SVG graphics: 1,269 · Rank 16 of 84, among scored models · Top 25% · Design Arena, read November 21, 2026

ASCII art: 1,255 · Rank 16 of 68, among scored models · Top 25% · Design Arena, read November 21, 2026

Cost of this job: $1.11

Models that score at least as high for less in this scenario: 30

Long documents

Declared, not measured

Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.

Cost of this job: $5.02

Images, files, audio, video in

Declared, not measured

Accepts: images, files, audio, and video. Declared by the provider through OpenRouter; we did not test it.

Cost of this job: $0.99Text-token prices only; images, audio and video may be billed separately.

The size of each job is our assumption; the prices are real.

  • Writing code: Requests: 40. Input tokens per request: 30,000. Output tokens per request: 1,500. Share of input served from cache: 70%.
  • Agents that use tools: Requests: 200. Input tokens per request: 45,000. Output tokens per request: 2,500. Share of input served from cache: 75%.
  • Websites and apps; Games and 3D; Slides and spreadsheets; Charts and graphics: Requests: 8. Input tokens per request: 12,000. Output tokens per request: 10,000. Share of input served from cache: 30%.
  • Long documents: Requests: 3. Input tokens per request: 400,000. Output tokens per request: 4,000. Share of input served from cache: 0%.
  • Images, files, audio, video in: Requests: 15. Input tokens per request: 20,000. Output tokens per request: 3,000. Share of input served from cache: 30%.

Thinking is billed as output tokens; a model that thinks longer costs more than this estimate. Ranks are among all models we list, including older ones. The share is rounded up to whole models, so a rank slightly past the exact share still counts. Models with equal scores share the better rank.

Price by provider

The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.

ProviderInputOutputCached inputMixedNotes
Google Vendor $2.00$12.00 $0.20 $4.50
Google AI Studio Vendor Price used here $2.00$12.00 $0.20 $4.50

Other pricing modes

Specifications

Context window
1M
Max output
66k
Accepts
text, images, files, audio, and video
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Always on
Thinking effort levels: low, medium, and high
Weights on Hugging Face
Not listed
Knowledge cutoff
No data
On OpenRouter since
February 19, 2026
Price check
confirmed

As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.

Benchmark scores

Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.

SourceScoreRank among scored
Coding Index
Artificial Analysis, read November 18, 2026
68.8Rank 16 of 86, among scored models Top 25%
Agentic Index
Artificial Analysis, read November 18, 2026
8.2Rank 39 of 64, among scored models
Websites
Design Arena, read November 21, 2026
1,240Rank 49 of 127, among scored models
UI components
Design Arena, read November 21, 2026
1,264Rank 35 of 118, among scored models
Game development
Design Arena, read November 21, 2026
1,181Rank 59 of 121, among scored models
3D scenes
Design Arena, read November 21, 2026
1,202Rank 46 of 114, among scored models
Data visualization
Design Arena, read November 21, 2026
1,233Rank 42 of 112, among scored models
SVG graphics
Design Arena, read November 21, 2026
1,269Rank 16 of 84, among scored models Top 25%
ASCII art
Design Arena, read November 21, 2026
1,255Rank 16 of 68, among scored models Top 25%
Code
Design Arena, read November 21, 2026
1,226Rank 50 of 122, among scored models
Web apps (agent)
Design Arena, read November 21, 2026
1,097Rank 35 of 47, among scored models
Full-stack apps (agent)
Design Arena, read November 21, 2026
1,041Rank 34 of 45, among scored models
Mobile apps (agent)
Design Arena, read November 21, 2026
1,084Rank 43 of 50, among scored models
Android apps (agent)
Design Arena, read November 21, 2026
1,034Rank 38 of 41, among scored models
Godot games (agent)
Design Arena, read November 21, 2026
1,129Rank 23 of 34, among scored models
Games (agent)
Design Arena, read November 21, 2026
1,061Rank 23 of 25, among scored models
Blender 3D (agent)
Design Arena, read November 21, 2026
1,037Rank 17 of 25, among scored models
PowerPoint files (agent)
Design Arena, read November 21, 2026
1,109Rank 24 of 29, among scored models
HTML slides (agent)
Design Arena, read November 21, 2026
1,054Rank 18 of 25, among scored models
Spreadsheets (agent)
Design Arena, read November 21, 2026
918Rank 32 of 32, among scored models
agents/agentichtmlslides
Design Arena, read November 21, 2026
1,226Rating 1,226; rank 4 at the source. Too few scored models for a tier.
agents/agenticslides
Design Arena, read November 21, 2026
1,112Rating 1,112; rank 7 at the source. Too few scored models for a tier.
agents/agenticslides(html)
Design Arena, read November 21, 2026
1,219Rating 1,219; rank 4 at the source. Too few scored models for a tier.
agents/agenticslides(python-pptx)
Design Arena, read November 21, 2026
1,107Rating 1,107; rank 7 at the source. Too few scored models for a tier.
agents/codetovideo
Design Arena, read November 21, 2026
1,119Rating 1,119; rank 21 at the source. Too few scored models for a tier.
agents/pdf
Design Arena, read November 21, 2026
1,098Rating 1,098; rank 40 at the source. Too few scored models for a tier.
agents/pptxslides
Design Arena, read November 21, 2026
1,110Rating 1,110; rank 7 at the source. Too few scored models for a tier.

Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.

Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab

Sources and dates

Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.