LangMart: MoonshotAI: Kimi K2 Thinking
Model Overview
| Property | Value |
|---|---|
| Model ID | openrouter/moonshotai/kimi-k2-thinking |
| Name | MoonshotAI: Kimi K2 Thinking |
| Provider | moonshotai |
| Released | 2025-11-06 |
Description
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.
Description
LangMart: MoonshotAI: Kimi K2 Thinking is a language model provided by moonshotai. This model offers advanced capabilities for natural language processing tasks.
Provider
moonshotai
Specifications
| Spec | Value |
|---|---|
| Context Window | 262,144 tokens |
| Modalities | text->text |
| Input Modalities | text |
| Output Modalities | text |
Pricing
| Type | Price |
|---|---|
| Input | $0.40 per 1M tokens |
| Output | $1.75 per 1M tokens |
Capabilities
- Frequency penalty
- Include reasoning
- Logit bias
- Logprobs
- Max tokens
- Min p
- Presence penalty
- Reasoning
- Repetition penalty
- Response format
- Seed
- Stop
- Structured outputs
- Temperature
- Tool choice
- Tools
- Top k
- Top logprobs
- Top p