Skip to content
AI Atlas
ModelDeprecatedOpen weightsIdentity probable

Kimi K2.5

Moonshot AIfamily · Kimihuggingface.co/moonshotai/Kimi-K2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Open in Graph
data quality72

Updated 5 h ago · first seen 11 Sept 2026

model_01M294WW5TTBRH9A6F6RZ9EH1W

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
2 quantizations0 official · 2 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
kimi-k2-5kimi-k2-5-non-reasoningmoonshotai/kimi-k2.5Identifiers under which providers and evaluators refer to this model.
Folded evaluation variants
1Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable under Other; 7 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

Licence: Other (unclassified licence) (unknown · stated as “other”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 h agomedium

Status

Source:Artificial AnalysisT2observed 13 h agomedium

Model card
huggingface.co/moonshotai/Kimi-K2.5

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 14 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
imagetext
Input
imagetext
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    Artificial Analysis · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Benchmarks32

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=v2.1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvariantv2.1reasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthardreasoningonconditions differ across rows → partially comparable4−31.1 ptvs gpt-5.6-solobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysis2−3.21 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
SWE-bench Multilingualcoding · resolved · board=Multilingual · system=mini-SWE-agentOfficial boardboardMultilingualsystemmini-SWE-agent1−5.40 ptvs gemini-3-flash13 Feb 2026swebench.comT2
SWE-bench Verifiedcoding · resolved · board=Verified · system=mini-SWE-agentOfficial boardboardVerifiedsystemmini-SWE-agentreasoning_efforthighconditions differ across rows → partially comparable1−6.00 ptvs Claude Opus 4.517 Feb 2026swebench.comT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable4−29.9vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−13.1 ptvs Grok 4.3obs. 12 Sept 2026artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−28.4 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−11.5 ptvs gpt-6-astraobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningonconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamond2−8.38 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 32 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing2

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
Moonshot AI Platformcheapest outputmoonshotai/kimi-k2.5262.1Kout 235.9K$0.07active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRoutermoonshotai/kimi-k2.5262.1Kout 235.9K$0.07active2 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Kimi K2.5$0$1$2$3Sept 26Sept 26Sept 26Sept 26Sept 26Moonshot AI Platform: first observed → $2.25 · 11 Sept 2026OpenRouter: first observed → $2.25 · 12 Sept 2026
  • Moonshot AI Platform
  • OpenRouter
  • OpenRouterfirst observed $2.2512 Sept 2026
  • Moonshot AI Platformfirst observed $2.2511 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Kimi K2.5$0$0.20$0.40$0.60Sept 26Sept 26Sept 26Sept 26Sept 26Moonshot AI Platform: first observed → $0.45 · 11 Sept 2026OpenRouter: first observed → $0.45 · 12 Sept 2026
  • Moonshot AI Platform
  • OpenRouter
  • OpenRouterfirst observed $0.4512 Sept 2026
  • Moonshot AI Platformfirst observed $0.4511 Sept 2026

Hardware fit37

Estimated

1 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
NVIDIA DGX B2004bit1,440 GB591.0 GB est.Yes
Apple M3 Ultra4bit—591.0 GB est.No
Mac Studio (Apple M5 Ultra)4bit—591.0 GB est.No
Apple M2 Ultra4bit—591.0 GB est.No
Apple M1 Ultra4bit—591.0 GB est.No
Apple M3 Max4bit—591.0 GB est.No
Apple M4 Max4bit—591.0 GB est.No
Mac Studio (Apple M5 Max)4bit—591.0 GB est.No
MacBook Pro (Apple M5 Max)4bit—591.0 GB est.No
Apple M2 Max4bit—591.0 GB est.No
Apple M1 Max4bit—591.0 GB est.No
Apple M4 Pro4bit—591.0 GB est.No
Mac mini (Apple M5 Pro)4bit—591.0 GB est.No
MacBook Pro (Apple M5 Pro)4bit—591.0 GB est.No
Apple M3 Pro4bit—591.0 GB est.No
Apple M1 Pro4bit—591.0 GB est.No
Apple M2 Pro4bit—591.0 GB est.No
Apple M44bit—591.0 GB est.No
iMac (Apple M4)4bit—591.0 GB est.No
Mac mini (Apple M6)4bit—591.0 GB est.No
MacBook Air (Apple M5)4bit—591.0 GB est.No
MacBook Pro (Apple M5)4bit—591.0 GB est.No
Apple M24bit—591.0 GB est.No
Apple M34bit—591.0 GB est.No
Apple M14bit—591.0 GB est.No
NVIDIA GeForce RTX 30904bit24 GB591.0 GB est.No
NVIDIA GeForce RTX 40904bit24 GB591.0 GB est.No
NVIDIA GeForce RTX 50904bit32 GB591.0 GB est.No
NVIDIA A100 80GB4bit80 GB591.0 GB est.No
NVIDIA H100 SXM4bit80 GB591.0 GB est.No
NVIDIA H100 NVL4bit94 GB591.0 GB est.No
NVIDIA DGX Spark4bit128 GB591.0 GB est.No
NVIDIA H2004bit141 GB591.0 GB est.No
NVIDIA H200 NVL4bit141 GB591.0 GB est.No
NVIDIA B2004bit180 GB591.0 GB est.No
AMD Instinct MI300X4bit192 GB591.0 GB est.No
AMD Instinct MI325X4bit256 GB591.0 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
DESCENDANTS 0 · ARTIFACTS2 quantizationsartifacts · collapsed2 quantizations — artifacts · collapsedKimi K2.51.03T params · this modelKimi K2.5 — 1.03T params · this model

    Versions & Artifacts2

    Version history

    Context window2 changes

    11 Sept 2026→11 Sept 2026→12 Sept 2026current

    Licensefirst observation only

    11 Sept 2026current

    Max outputfirst observation only

    11 Sept 2026current

    Opennessfirst observation only

    11 Sept 2026current

    Parametersfirst observation only

    11 Sept 2026current

    Statusfirst observation only

    11 Sept 2026current

    Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

    Artifacts 2

    quantizations 2

    Papers1

    Timeline20

    Full timeline →

    Change history

    Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
    1 claims · 1 propertiesShow all properties

    Aa context windowaa_context_window1

    Claim history for Aa context window
    ValueValid from → toStatusSourceConfidenceExtractor
    256,000 tokens → currentcurrentArtificial AnalysisT2mediumdeterministic

    Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

    Provenance

    Attributed facts

    40

    Source tiers

    T240

    Freshest observation

    5 h ago

    Conflicts

    None

    Source documents 8

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/moonshotai/Kimi-K2.5 model_pageT2· Quality secondary23 min ago6
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/mlx-community/Kimi-K2.5 model_pageT2· Quality secondary24 min ago5
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/amd/Kimi-K2.5-MXFP4 model_pageT2· Quality secondary49 min ago7
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=moonshotai&p=0&sort=downloads listingT2· Quality secondary52 min ago8
    OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago11
    SWE-bench leaderboardsswebench.com/ leaderboardT2· Quality secondary5 h ago1
    Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary5 h ago2
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/moonshotai/Kimi-K2.5/raw/main/README.md model_cardT2· Quality secondary8 h ago1

    Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

    Data quality (72/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →