MoonshotAI: Kimi K2 Thinking

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.

Raw fields snapshot

{
  "id": "moonshotai/kimi-k2-thinking",
  "canonical_slug": "moonshotai/kimi-k2-thinking-20251106",
  "name": "MoonshotAI: Kimi K2 Thinking",
  "display_name": "MoonshotAI: Kimi K2 Thinking",
  "provider": "moonshotai",
  "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.\n\nIt 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.",
  "context_length": null,
  "source_type": "model_only",
  "best_rank": null,
  "pricing": {
    "prompt": null,
    "completion": null
  },
  "pricing_summary": {},
  "capabilities": {
    "modalities": [
      "text"
    ],
    "context_length": null,
    "architecture": {
      "modality": "text->text",
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Other",
      "instruct_type": null
    }
  },
  "__detail_source": "model_snapshot",
  "__raw_snapshot": {
    "model": {
      "id": "moonshotai/kimi-k2-thinking",
      "slug": "moonshotai/kimi-k2-thinking-20251106",
      "display_name": "MoonshotAI: Kimi K2 Thinking",
      "provider": "moonshotai",
      "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.\n\nIt 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.",
      "context_length": null,
      "modalities": [
        "text"
      ],
      "tags": [],
      "source_type": "model_only",
      "updated_at": "2026-03-01T02:42:36.926566+00:00",
      "source": "model_only"
    },
    "overall_score": null,
    "best_rank": null,
    "ranks_by_category": {},
    "scores_by_category": {},
    "pricing_summary": {},
    "capabilities": {
      "modalities": [
        "text"
      ],
      "context_length": null,
      "architecture": {
        "modality": "text->text",
        "input_modalities": [
          "text"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Other",
        "instruct_type": null
      }
    }
  }
}