Gemini 3.1 Pro
Language modelCard summarizedGoogle's most advanced model for complex tasks
Preview● Re-checked 12 Oct 2026 · 72 facts · 0 corrections · 1 unconfirmedSource: Gemini 3.1 Pro Model Card (9 pp)
Use it via API
$1,236 /month
$24.72 per 1K requests
RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change
Where to call it
- Gemini API
gemini-3.1-pro-preview - Google Vertex AI
gemini-3.1-pro-preview
Supports
- Structured outputs
- Reasoning control
- Tool calling
- Prompt caching
- Batch API
- Image input
- PDF input
Good for
- Agentic performance
- Advanced coding
- Long context and multimodal understanding
Overview
Google · 04Pro, front
Gemini 3.1 Pro
Google's most advanced model for complex tasks
- Cost
- $2.00 in
- Context
- 1M
- Input / output
- $2.00 / $12.00
- Max output
- 64K
- Knows up to
- January 2025
- Released
- 19 Feb 2026
The next iteration in the Gemini 3 series of natively multimodal reasoning models and, when the card was published, Google's most advanced model for complex tasks. It can work across text, audio, images, video and entire code repositories. p.2
gemini-3.1-pro-preview- Input / output per 1M
- $2.00 / $12.00
- Context window
- 1M
- Max output
- 64K
- Knows up to
- January 2025
- Reasoning
- Dynamic, thinking_level low / medium / high
- Weights
- Closed
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Google DeepMind's Gemini 3.1 Pro Model Card. Every claim carries its source page.