← Back to all models
Reasoning-specialized model trained with reinforcement learning. Shows chain-of-thought reasoning transparently.
#reasoning#rl-trained#open-weight#chain-of-thought
🧮
671B
Parameters
📏
128K tokens
Context Window
🔓
Open Source
License
📅
Jan 20, 2025
Released
💰 Pricing
Input
$0.55
per 1M tokens
Output
$2.19
per 1M tokens
⚡ Strengths
✓Transparent reasoning chains
✓Strong at math/logic
✓Open weights
✓RL-trained
🎯 Use Cases
Math competitionsLogic puzzlesScientific reasoningResearch
🔌
API Available
This model is accessible via API for integration into your applications.
⭐ Related Models
🧠
Claude 4 Opus
Anthropic
🔥 98
Anthropic's most powerful reasoning model with extended thinking. Excels at complex analysis, multi-step math, advanced coding, and nuanced writing.
🔒 proprietary📏 200K ctx💰 $15
Sep 1, 2025View details →
🧠
Claude 4 Sonnet
Anthropic
🔥 94
Balanced intelligence and speed. Strong reasoning with faster response times and lower cost than Opus.
🔒 proprietary📏 200K ctx💰 $3
Jun 1, 2025View details →
🧠
o3
OpenAI
🔥 91
OpenAI's most powerful reasoning model. Uses chain-of-thought to solve complex math, science, and coding problems.
🔒 proprietary📏 200K ctx💰 $10
Apr 16, 2025View details →