Kimi K2 Thinkingon Krater.ai
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
Released November 6, 2025
Specifications
Kimi K2 Thinking at a glance
Context
262.1K tokens
Max output
100.4K tokens
Input
Text
Output
Text
Input price
$0.60 / 1M
Output price
$2.50 / 1M
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
21
Agentic index score
1.8
Intelligence index score
17.3
Design Arena website rank
#80
Compare
Compare Kimi K2 Thinking
Kimi K2 Thinking vs Kimi K2 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.
Open comparisonKimi K2 Thinking vs Kimi K2 0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32
Open comparisonKimi K2 Thinking vs Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
Open comparisonFAQ
Questions about Kimi K2 Thinking
Clear answers based on the model catalog and Krater access.
Use Kimi K2 Thinking in your API
Connect with Krater's unified API.
Ready to use Kimi K2 Thinking?
Access leading models in one focused workspace.