Kimi K2 Thinking

moonshotai/kimi-k2-thinking-20251106

MoonshotAI: Kimi K2 Thinking is a text‑only model from MoonshotAI released on 2025‑11‑06, supporting tools and reasoning with open weights. It offers a context length of 262 144 tokens and is priced at $0.6 per million input tokens and $2.5 per million output tokens.

  • tool use
  • structured outputs
  • reasoning

At a glance

providermoonshotai
releasedNov 1, 2024
context262K
input / M$0.60

Specifications

What the API gives you

Context window
262K tokens
Max output
100K tokens
Input price
$0.60 / 1M tokens
Output price
$2.50 / 1M tokens
Cache read
$0.15 / 1M tokens
Modalities
text → text
Knowledge cutoff
—
Released
Nov 1, 2024

Measured evidence

Public benchmark record

Aider Polyglot
59.1%2026-07-17
Aider Polyglot
59.1%2026-07-21
Aider Polyglot
59.1%2026-07-23
Design Arena Website
1138 Elo2026-07-28
Design Arena Website
1138 Elo2026-07-30
Design Arena Website
1138 Elo2026-07-27
Design Arena Website
1138 Elo2026-07-29
Design Arena Website
1137 Elo2026-07-31
Design Arena Website
1137 Elo2026-08-02
Design Arena Website
1137 Elo2026-08-01
Design Arena Website
1136 Elo2026-08-05
Design Arena Website
1137 Elo2026-08-03
Design Arena Website
1135 Elo2026-08-09
Design Arena Website
1137 Elo2026-08-04
Design Arena Website
1133 Elo2026-08-14
Design Arena Website
1136 Elo2026-08-06
Design Arena Website
1136 Elo2026-08-07
Design Arena Website
1135 Elo2026-08-10
Design Arena Website
1135 Elo2026-08-08
Design Arena Website
1124 Elo2026-08-18
Design Arena Website
1135 Elo2026-08-11
Design Arena Website
1124 Elo2026-08-15
Design Arena Website
1134 Elo2026-08-12
Design Arena Website
1133 Elo2026-08-13
Design Arena Website
1124 Elo2026-08-19
Design Arena Website
1124 Elo2026-08-16
Design Arena Website
1124 Elo2026-08-20
Design Arena Website
1133 Elo2026-08-27
Design Arena Website
1124 Elo2026-08-17
Design Arena Website
1128 Elo2026-09-05
Design Arena Website
1133 Elo2026-08-21
Design Arena Website
1133 Elo2026-08-22
Design Arena Website
1133 Elo2026-08-23
Design Arena Website
1133 Elo2026-08-24
Design Arena Website
1133 Elo2026-08-28
Design Arena Website
1133 Elo2026-08-25
Design Arena Website
1133 Elo2026-08-26
Design Arena Website
1126 Elo2026-09-06
Design Arena Website
1132 Elo2026-08-29
Design Arena Website
1132 Elo2026-08-30
Design Arena Website
1132 Elo2026-08-31
Design Arena Website
1132 Elo2026-09-01
Design Arena Website
1131 Elo2026-09-02
Design Arena Website
1129 Elo2026-09-03
Design Arena Website
1128 Elo2026-09-04
SWE-rebench‡
47.8% ± 1.22026-03-01tools

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Debugging & Code ReviewEstablished evidence

    60% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    56% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    36% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Design Arena Coding or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    15% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Coding or Design Arena UI. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for High-Volume ExtractionProvisional evidence

    13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.

  • Best LLM for Literary TranslationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Everyday TranslationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document SummarizationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Image UnderstandingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Vision & DocumentsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

  • Best LLM for Roleplay & CharacterProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best Open-Weight LLM for Self-HostingProvisional evidence

    8% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Long Query. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for RAG & Long ContextProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for JSON & Schema OutputProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.