Gemini 2.5 Pro
google/gemini-2.5-pro
Gemini with step-by-step thinking for math, science and code.
MultimodalText, Images, Files, Audio, Video → TextReady on endue
- Reasoning
- Audio & video
- Long documents
Overview
Good for
Written by endue
- Reasoning
- Audio & video
- Long documents
Not ideal for
From the model’s specs
Nothing in the specs rules out common agent work.
Capabilities
| Tool use | Supported |
|---|---|
| Structured output | Supported |
| JSON mode | Supported |
| Reasoning | Supported |
| Vision | Supported |
| Audio input | Supported |
| Video input | Supported |
| File input | Supported |
| Long context | Supported |
Specifications
- Model ID
google/gemini-2.5-pro- Family
- Gemini Pro
- Context window
- 1M tokens
- Input
- Text, Images, Files, Audio, Video
- Output
- Text
- Knowledge cutoff
- 2026-01
- Released
- 2026-03-05