All models
Gemini 2.5 Pro Experimental
Vision Google
Claude 3.5 Sonnet Frontier Claude 3.7 Sonnet Frontier Claude 3.7 Sonnet (high output) Frontier Claude 3.7 Sonnet (thinking) Frontier Claude Opus Frontier Gemini 2.5 Pro Frontier GPT-4.1 Frontier GPT-4o Frontier o1 Frontier o1-mini Frontier

Gemini 2.5 Pro Experimental

Experimental release (March 25th, 2025) of Gemini 2.5 Pro

Model Specifications

Context window 1,000,000 tokens
Max output 60,000 tokens
Knowledge cutoff March 2025
Multipart messages No
Vision capabilities Yes

Default Parameters

Temperature 0.3
Top P 1.0
Top K 50
Try on Simtheory

Supported Parameters

Temperature

Supported

Controls randomness: Lower values make output more deterministic, higher values more creative.

Range: 0.0 - 1.0 Default: 0.3

More models from Google

Gemini 2.5 Pro

Gemini 2.5 Pro Frontier Vision

A powerful reasoning model with 1M token context designed for advanced problem-solving tasks and multimodal capabilities.

Context: 1,000,000 Output: 60,000
Gemini 2.5 Flash Experimental

Gemini 2.5 Flash Experimental Vision

Multimodal model that is fast, token efficient and performant for complex tasks. 1M context window.

Context: 1,048,576 Output: 64,000
Gemini Flash Lite Preview

Gemini Flash Lite Preview Vision

Google's small fast model updated to 2.0. Features reduced latency and memory requirements while maintaining strong performance on common tasks.

Context: 1,048,576 Output: 8,192