DeepYard
o

o3 Pro

13

The o-series of models are trained with reinforcement learning to think before t...

commercialpaid

About

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers. Note that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations

Details

Modalityimage, file, text
Context Window200.0K tokens
Release DateJun 10, 2025
API AvailableYes
Hostingapi
Output Speed50 tokens/sec
Time to First Token8000ms
Quality Index92/100
Coding Index86/100
Reasoning Index99/100

Benchmarks

Chatbot Arena ELO
1460/1500
MMLU-Pro
88/100
MATH-500
98.1/100
GPQA Diamond
86/100
AIME 2025
99.2/100

Tags

multimodalreasoningapichatfrontiercoding