Kimi K2 Thinking
About this model
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
Performance Tier
Kimi K2 Thinking is a balanced model from MoonshotAi : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.470 |
| Output (completion) | $2.00 |
| Cache read | $0.141 |
Capabilities
Benchmarks
Recommended Use Cases
Strengths
- Extended thinking mode for complex reasoning tasks
- Strong mathematical reasoning capabilities
- Transparent chain-of-thought process
Limitations
- Slower than standard Kimi K2 due to thinking overhead
- Less suited for quick conversational interactions
Resources
This model may use your data for training
