Test AI models v2.0 is hereSee what's new
Test AI models
Google

Gemini 3.1 Pro Preview on your prompt

Google's advanced preview model for complex reasoning and multi-step tasks.

PremiumVisionReasoningAdded Jul 30, 2026
1M
tokens of context. Low, Medium or High effort. Reads images and PDFs.

What it can do at a glance

Facts from the platform's model list. Prices change, so the app shows the live price when you pick the model.

Context window1Mtokens in one request
ReasoningLow, Medium or High effort
VisionReads images and PDFs

Tasks and formats it handles

Task types

  • Reasoning
  • Generation

Input

  • Text
  • Image

Output

  • Text

See how it does on your own prompt

A benchmark tells you how a model did on someone else's questions. A test tells you how it does on yours.

1

Paste your prompt

Use the prompt you run in production. No API keys needed.

2

Add Gemini 3.1 Pro Preview and others

Pick up to 10 models on Pay as you go and up to 20 on PRO.

3

Read answers side by side

See each answer with its cost, speed and tokens, then check them against a rule you write.

More from Google

All models

Questions about Gemini 3.1 Pro Preview

What is the context window of Gemini 3.1 Pro Preview?

1M tokens.

Can Gemini 3.1 Pro Preview read images?

Yes, it reads images and PDFs. Each PDF page is read as an image.

Can I set the reasoning effort of Gemini 3.1 Pro Preview?

Low, Medium or High effort. The app offers only the settings this model accepts.

How much does Gemini 3.1 Pro Preview cost?

Providers change their prices, so this page does not print one. When you pick the model in the app you see its live price per 1M tokens, and an estimate in credits before every run.

Is Gemini 3.1 Pro Preview available on both plans?

Yes. No plan locks a model. Pay as you go runs up to 10 models per test and PRO up to 20.

Find the cheaper model before your next invoice

  • 10k free credits
  • No card
  • No API keys
Run your first test free