Skip to content
AI Atlas
ModelDeprecatedOpen weightsIdentity probable

Kimi K2.6

Moonshot AIfamily · Kimihuggingface.co/moonshotai/Kimi-K2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Open in Graph
data quality72

Updated 3 h ago · first seen 11 Sept 2026

model_01M294AJ0JZ1E1XNZT6ENGD6MQ

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
1 quantization0 official · 1 third-partySeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
3
API aliases
fireworks/kimi-k2p6kimi-k2-6kimi-k2-6-non-reasoningmoonshotai/kimi-k2.6Identifiers under which providers and evaluators refer to this model.
Folded evaluation variants
2Effort / 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 8 h agomedium

Status

Source:Artificial AnalysisT2observed 11 h agomedium

Model card
huggingface.co/moonshotai/Kimi-K2.6

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 13 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 10 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 13 h agomedium

Benchmarks38

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 comparable4−22.0 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
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−30.4 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−7.81 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
SciCodecoding · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−11.6 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningonversion4.3conditions differ across rows → partially comparable4−22.0vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBenchgeneral · global_averageOfficial boardreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−12.9 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−17.8 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagereasoningonrelease2026-06-25conditions differ across rows → partially comparable1−15.5 ptvs Claude Fable 525 Jun 2026livebench.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−7.34 ptvs Grok 4.3obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−17.1 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable4−21.6 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−12.7 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningonconditions differ across rows → partially comparable2−7.52 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 Diamond2−5.15 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningreasoningonrelease2026-06-25conditions differ across rows → partially comparable1−13.3 ptvs gpt-6-astra25 Jun 2026livebench.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. 38 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 & Pricing3

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
Fireworks AIcheapest outputfireworks/kimi-k2p6—$0.16active5 h agosince 11 Sept 2026app.fireworks.aiT1
Moonshot AI Platformmoonshotai/kimi-k2.6262.1Kout 235.9K$0.16active3 h agosince 11 Sept 2026openrouter.aiT2
OpenRoutermoonshotai/kimi-k2.6262.1Kout 235.9K$0.16active20 min 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 3 providers

Output price history of Kimi K2.6$0$1$2$3$4$5Sept 26Sept 26Sept 26Sept 26Fireworks AI: first observed → $4 · 11 Sept 2026Moonshot AI Platform: first observed → $4 · 11 Sept 2026OpenRouter: first observed → $4 · 12 Sept 2026
  • Fireworks AI
  • Moonshot AI Platform
  • OpenRouter
  • OpenRouterfirst observed $412 Sept 2026
  • Moonshot AI Platformfirst observed $411 Sept 2026
  • Fireworks AIfirst observed $411 Sept 2026

Input price · USD / 1M tokens 3 providers

Input price history of Kimi K2.6$0$0.20$0.40$0.60$0.80$1$1.2Sept 26Sept 26Sept 26Sept 26Fireworks AI: first observed → $0.95 · 11 Sept 2026Moonshot AI Platform: first observed → $0.95 · 11 Sept 2026OpenRouter: first observed → $0.95 · 12 Sept 2026
  • Fireworks AI
  • Moonshot AI Platform
  • OpenRouter
  • OpenRouterfirst observed $0.9512 Sept 2026
  • Moonshot AI Platformfirst observed $0.9511 Sept 2026
  • Fireworks AIfirst observed $0.9511 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 · ARTIFACTS1 quantizationartifacts · collapsed1 quantization — artifacts · collapsedKimi K2.61.03T params · this modelKimi K2.6 — 1.03T params · this model

    Versions & Artifacts1

    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 1

    quantization 1

    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

    Gatedgated1

    Claim history for Gated
    ValueValid from → toStatusSourceConfidenceExtractor
    No → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

    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

    42

    Source tiers

    T242

    Freshest observation

    3 h ago

    Conflicts

    None

    Source documents 8

    Source documents
    SourceDocumentTypeTierLast observedSnapshots
    Fireworks AI — pricingdocs.fireworks.ai/serverless/pricing.md pricingT1· Official2 h ago2
    OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary20 min ago10
    Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary3 h ago2
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=moonshotai&p=0&sort=downloads listingT2· Quality secondary3 h ago7
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/moonshotai/Kimi-K2.6/raw/main/README.md model_cardT2· Quality secondary6 h ago1
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/moonshotai/Kimi-K2.6 model_pageT2· Quality secondary6 h ago5
    Hugging Face Hub (public pages, model cards, papers)huggingface.co/amd/Kimi-K2.6-MXFP4 model_pageT2· Quality secondary7 h ago6
    LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary11 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 →