In the rapidly evolving landscape of AI, “reasoning models” like DeepSeek R1 have emerged as powerful thinkers. They excel at complex logic, math, and planning. However, a common challenge has been integrating these deep thinkers with practical tool execution.

Recently, we implemented a novel approach in our system that leverages the best of both worlds: the planning capability of reasoning models and the robust execution capability of standard chat models.

In our application, we use several AI models with different pricing structures. Here’s the current pricing in USD per 1M tokens:

Instruction Models

• Input: $0.48/1M tokens
• Output: $1.92/1M tokens

Reasoning Models

• Input: $0.96/1M tokens
• Output: $3.84/1M tokens

Vision Models

• Input: $0.72/1M tokens
• Output: $2.16/1M tokens

Additional Models

• Anthropic Claude Sonnet 4.5
  • Input: $15.6/1M tokens
  • Output: $57.2/1M tokens
• OpenAI GPT-5
  • Input: $3.2/1M tokens
  • Output: $26/1M tokens
• OpenAI GPT-OSS-120B
  • Input: $0.1/1M tokens
  • Output: $1/1M tokens

Currency Conversion

Current USD to credits rate: 1 USD = 500 credits

DeepSeek’s latest V3.1 stable version and V3.2 experimental version achieve breakthroughs in reasoning and programming capabilities