modelgrep
G

Google: Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview

41st smartest of 179ReasoningToolsJSONVisionAudio
Use via OpenRouter ↗
Intelligence
41.3
41st of 179
Design Elo
1345
svg
Speed
74
104th fastest
Latency
3.8s
first token
Input price
$2.00
241st cheapest
Context
1.0M
66K max out

How it compares

Smarter than77%
of all ranked models
Faster than66%
of all ranked models
Cheaper than19%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis75th percentile
Intelligence Index
41.3
Coding Index
39.4
Agentic Index
45.0
GPQA Diamond
89%
Humanity's Last Exam
28%
SciCode
50%
Tau²-Bench (agentic)
68%
Design Arena · Elo32,058 tournaments
UI Component
1323
asciiart
1312
3D
1302
svg
1302
Website
1296
codecategories
1293
Data Viz
1270
Game Dev
1263
agentichtmlslides
1226
godotgamedev
1221
agenticslides(html)
1219
webapps
1211
mobileapps
1183
fullstack
1151
agenticgamedev
1149
agenticslides(python-pptx)
1116
agenticslides
1112
androidnative
1065

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Google AI Studio$2.00$12.0099.5%
Google$2.00$12.0097.5%

Specifications

Context window1.0M
Max output66K
Knowledge cutoff
Input modalitiesaudio, file, image, text, video
Output modalitiestext
Prompt caching
Cache read price$0.200/M
ModeratedNo

Gemini 3.1 Pro Preview FAQ

How much does Gemini 3.1 Pro Preview cost?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens via OpenRouter, making it 241st cheapest of 298 paid models.

How smart is Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview scores 41.3 on the Artificial Analysis Intelligence Index, ranking 41st of 179 benchmarked models, with a GPQA Diamond score of 89%.

How fast is Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview generates around 74 tokens per second with 3.8s time-to-first-token (p50), the 104th fastest tracked model.

What is Gemini 3.1 Pro Preview's context window?

Gemini 3.1 Pro Preview supports a 1.0M-token context window and can output up to 66K tokens. It accepts audio, file, image, text, video input.

Compare head-to-head