Gemini 3.1 Pro
Gemini 3.1 Pro is Google's flagship reasoning model in Armox for multimodal work across text, images, video, and audio.
Overview
| Property | Value |
|---|---|
| Provider | |
| Cost | 25 credits |
| Modality | Text |
| Vision | Yes (images and videos) |
| Audio Input | Yes |
| Thinking Levels | low, medium, high |
| Default Thinking | medium |
Inputs
- Prompt (required)
- System Instruction (optional)
- Images (optional, up to model limits)
- Videos (optional, up to model limits)
- Audio (optional)
- PDF Input (optional, OCR text is appended to prompt)
Configuration
- Thinking Level:
low,medium,high - Temperature: 0 to 2
- Top P: 0 to 1
- Max Output Tokens: up to 65,535
Best For
- Multimodal analysis with images and video
- Complex reasoning with balanced speed
- Audio-aware prompt workflows
- General purpose text generation with strong quality/cost balance