Kimi K2.5

moonshotai/kimi-k2.5-0127

MoonshotAI's Kimi K2.5 model processes text and image inputs to generate text outputs. It has a context length of 262,144 tokens and supports tools and reasoning. Input pricing is $0.50 per million tokens, while output pricing is $2.50 per million tokens; it is an open-weight model.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providermoonshotai
releasedJan 27, 2026
context262K
input / M$0.50

Specifications

What the API gives you

Context window
262K tokens
Max output
236K tokens
Input price
$0.50 / 1M tokens
Output price
$2.50 / 1M tokens
Cache read
$0.15 / 1M tokens
Modalities
text, image → text
Knowledge cutoff
—
Released
Jan 27, 2026

Measured evidence

Public benchmark record

Design Arena Coding
1226 Elo2026-11-15
Design Arena UI
1226 Elo2026-11-15
Design Arena Web-app Agent
1112 Elo2026-11-15
Design Arena Website
1240 Elo2026-11-15
LMArena Creative Writing
1422 Elo2026-11-11
LMArena Long Query
1444 Elo2026-11-11
LMArena Math
1469 Elo2026-11-11
LMArena Text
1450 Elo2026-11-11
LMArena Text Factuality
1445 Elo2026-11-11
LMArena Vision
1252 Elo2026-11-09
LMArena Vision Diagrams
1280 Elo2026-11-09
LMArena Vision OCR
1266 Elo2026-11-09
LMArena WebDev
1436 Elo2026-11-11
LMArena WebDev Image-to-Web
1439 Elo2026-11-10
SimpleQA Verified (Epoch AI)
34.3% ± 1.52026-08-27evaluated 2026-08-27
SWE-bench Verified (verified-500)‡
70.8%2026-11-15mini-SWE-agent 2.0.0, high effort, evaluated 2026-02-17

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 Frontend & UIEstablished evidence

    91% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • 59% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    42% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 5 of 7 configured evaluation feeds currently have results.

  • 28% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

Show all 36 tasks
  • Best LLM for Marketing CopyProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • 67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • 60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    58% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 5 of 6 configured evaluation feeds currently have results.

  • 39% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 5 of 6 configured evaluation feeds currently have results.

  • 36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from GPQA Diamond (Epoch AI) or LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    28% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FrontierMath Tiers 1-3 (Epoch AI) or GPQA Diamond (Epoch AI). 7 of 7 configured evaluation feeds currently have results.

  • 27% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    26% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FrontierMath Tiers 1-3 (Epoch AI) or OTIS Mock AIME (Epoch AI). 6 of 6 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

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

  • Best LLM for Fast SummariesProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • 17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • 12% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 3 of 4 configured evaluation feeds currently have results.

  • 12% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 3 of 4 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 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.