Model Overview
Gemini 2.5 Pro is Google's state-of-the-art thinking model with maximum response accuracy and enhanced reasoning capabilities for complex problems.
Key Features
- Very high intelligence (4/4 dots rating)
- Medium speed (3/5 lightning bolts rating)
- 1,048,576 context window
- 65,536 max output tokens
- January 2025 knowledge cutoff
- Audio, images, video, and text input support
- Text output support
Technical Specifications
- Model Code: gemini-2.5-pro-preview-05-06
- Supports: Input: audio, images, video, text; Output: text only
- Features: Structured outputs, caching, function calling, code execution, search grounding, thinking
- Pricing:
- Input: $1.25 per 1M tokens (≤200k prompts), $2.50 per 1M tokens (>200k prompts)
- Output: $10.00 per 1M tokens (≤200k prompts), $15.00 per 1M tokens (>200k prompts)
- Context caching: $0.31 per 1M tokens (≤200k), $0.625 per 1M tokens (>200k), $4.50/1M tokens per hour storage
- TTS: $1.00 input, $20.00 output per 1M tokens
- Free Tier: Not available
Snapshots
- gemini-2.5-pro-preview-05-06
Positioning and Use Cases
Gemini 2.5 Pro is capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context. Best for complex coding, reasoning, and multimodal understanding tasks that require maximum accuracy and state-of-the-art performance.
Rate Limits
- More restricted rate limits since it is a preview model
Documentation
Official Documentation
