Cracked AI Engineering

Kimi K2 Instruct

Nvidia

The Kimi K2 Instruct AI model by Nvidia offers advanced reasoning capabilities with a context window of 128,000 tokens and an output limit of 8,192 tokens. Developers can leverage this model for text input, function calling, and complex reasoning tasks. With open weights, competitive pricing, and a training data cutoff set for 2024, the Kimi K2 is a powerful tool for building sophisticated AI applications.

Key Specifications

Context Window

128K tokens

Max Output Tokens

8K tokens

Input Pricing

Free

per million tokens

Output Pricing

Free

per million tokens

Capabilities

  • Text Generation
  • Function Calling
  • Advanced Reasoning

Additional Details

Provider
Nvidia
Release Date
January 1, 2025
Advanced Reasoning
Supported
Supported Input Types
text

Compare with Similar Models