Overview

Identity

Canonical model: Yesidentity confidence: high
Official checkpoints: moonshotai/Kimi-K2-Instruct-0905
Artifacts: None recorded
Provider deployments: 1
API aliases: kimi-k2-0905moonshotai/kimi-k2-0905
Folded evaluation variants: 0

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
Knowledge cutoff: Source:OpenRouter public model & pricing listingT2observed 15 h agomedium
Model card: huggingface.co/moonshotai/Kimi-K2-Instruct-0905
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: text
Input: text
Output: text

Capabilities

Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
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
Knowledge cutoff: Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Benchmarks6

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 · group	Trust	Configuration	Results	vs leader	Evaluated	Source
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysisvarianthard	1	−42.4 ptvs gpt-5.6-sol	obs. 11 Sept 2026	artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysis	1	−25.7 ptvs Z.ai GLM 5.2	obs. 11 Sept 2026	artificialanalysis.aiT2
Artificial Analysis Intelligence Indexcomposite · index	Independent	version4.3	1	−38.1vs Claude Fable 5.1	obs. 11 Sept 2026	artificialanalysis.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysis	1	−41.6 ptvs Grok 4.3	obs. 11 Sept 2026	artificialanalysis.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial Analysis	Independent	evaluatorArtificial Analysis	1	−52.7 ptvs Claude Fable 5.1	obs. 11 Sept 2026	artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial Analysis	Independent	evaluatorArtificial AnalysisvariantGPQA Diamond	1	−19.6 ptvs gpt-6-astra	obs. 11 Sept 2026	artificialanalysis.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. 6 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 & Pricing1

All offers in the price terminal →

Provider deployments, cheapest output first
Provider	Context	Input / 1M	Output / 1M	Status	Observed	Source
Moonshot AI Platformcheapest outputmoonshotai/kimi-k2-0905	262.1Kout 100.3K			active	6 h agosince 11 Sept 2026	openrouter.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 1 provider

Moonshot AI Platform

Moonshot AI Platformfirst observed $2.511 Sept 2026

Input price · USD / 1M tokens 1 provider

Moonshot AI Platform

Moonshot AI Platformfirst observed $0.6011 Sept 2026

Hardware fit37

Estimated

1 of 37 device × quantization combinations fit.

Run locally: your machine →

Estimated hardware fit
Hardware	Quantization	Device memory	Est. memory	Fits
NVIDIA DGX B200	4bit	1,440 GB	590.7 GB est.	Yes
Apple M3 Ultra	4bit	—	590.7 GB est.	No
Mac Studio (Apple M5 Ultra)	4bit	—	590.7 GB est.	No
Apple M2 Ultra	4bit	—	590.7 GB est.	No
Apple M1 Ultra	4bit	—	590.7 GB est.	No
Apple M3 Max	4bit	—	590.7 GB est.	No
Apple M4 Max	4bit	—	590.7 GB est.	No
Mac Studio (Apple M5 Max)	4bit	—	590.7 GB est.	No
MacBook Pro (Apple M5 Max)	4bit	—	590.7 GB est.	No
Apple M2 Max	4bit	—	590.7 GB est.	No
Apple M1 Max	4bit	—	590.7 GB est.	No
Apple M4 Pro	4bit	—	590.7 GB est.	No
Mac mini (Apple M5 Pro)	4bit	—	590.7 GB est.	No
MacBook Pro (Apple M5 Pro)	4bit	—	590.7 GB est.	No
Apple M3 Pro	4bit	—	590.7 GB est.	No
Apple M1 Pro	4bit	—	590.7 GB est.	No
Apple M2 Pro	4bit	—	590.7 GB est.	No
Apple M4	4bit	—	590.7 GB est.	No
iMac (Apple M4)	4bit	—	590.7 GB est.	No
Mac mini (Apple M6)	4bit	—	590.7 GB est.	No
MacBook Air (Apple M5)	4bit	—	590.7 GB est.	No
MacBook Pro (Apple M5)	4bit	—	590.7 GB est.	No
Apple M2	4bit	—	590.7 GB est.	No
Apple M3	4bit	—	590.7 GB est.	No
Apple M1	4bit	—	590.7 GB est.	No
NVIDIA GeForce RTX 3090	4bit	24 GB	590.7 GB est.	No
NVIDIA GeForce RTX 4090	4bit	24 GB	590.7 GB est.	No
NVIDIA GeForce RTX 5090	4bit	32 GB	590.7 GB est.	No
NVIDIA A100 80GB	4bit	80 GB	590.7 GB est.	No
NVIDIA H100 SXM	4bit	80 GB	590.7 GB est.	No
NVIDIA H100 NVL	4bit	94 GB	590.7 GB est.	No
NVIDIA DGX Spark	4bit	128 GB	590.7 GB est.	No
NVIDIA H200	4bit	141 GB	590.7 GB est.	No
NVIDIA H200 NVL	4bit	141 GB	590.7 GB est.	No
NVIDIA B200	4bit	180 GB	590.7 GB est.	No
AMD Instinct MI300X	4bit	192 GB	590.7 GB est.	No
AMD Instinct MI325X	4bit	256 GB	590.7 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.

Versions & Artifacts0

Version history

Context window2 changes

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

Knowledge cutofffirst observation only

11 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 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline3

Full timeline →

12 Sept 2026
Context window changedModelKimi K2 0905Moonshot AI
Kimi K2 0905: context length changed from 256000 to 262144
Context window256K tokens→262.1K tokensopenrouter
openrouter.ai
11 Sept 2026
Release date changedModelKimi K2 0905Moonshot AI
Kimi K2 0905: release date changed from 2025-09-03 to 2025-09-04
Release date3 Sept 2025→4 Sept 2025openrouter
openrouter.ai
11 Sept 2026
Release date changedModelKimi K2 0905Moonshot AI
Kimi K2 0905: release date changed from 2025-09-04 to 2025-09-03
Release date4 Sept 2025→3 Sept 2025huggingface
huggingface.co

Change history44

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

Viewing AI Atlas as of 12 Mar 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Kimi K2 0905 was not yet in AI Atlas on 12 Mar 2026

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.

44 claims · 37 properties

Release daterelease_date6

Claim history for Release date
Value	Valid from → to	Status	Source	Confidence	Extractor
3 Sept 2025	12 Sept 2026 02:05 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
4 Sept 2025	12 Sept 2026 00:05 UTC → 12 Sept 2026 02:05 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic
3 Sept 2025	11 Sept 2026 23:18 UTC → 12 Sept 2026 00:05 UTC	superseded	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
4 Sept 2025	11 Sept 2026 22:37 UTC → 11 Sept 2026 23:18 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic
3 Sept 2025	11 Sept 2026 21:50 UTC → 11 Sept 2026 22:37 UTC	superseded	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic
4 Sept 2025	11 Sept 2026 21:10 UTC → 11 Sept 2026 21:50 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic

Statusstatus1

Claim history for Status
Value	Valid from → to	Status	Source	Confidence	Extractor
deprecated	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Opennessopenness1

Claim history for Openness
Value	Valid from → to	Status	Source	Confidence	Extractor
open-weights	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Licenselicense1

Claim history for License
Value	Valid from → to	Status	Source	Confidence	Extractor
other	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Architecturearchitecture1

Claim history for Architecture
Value	Valid from → to	Status	Source	Confidence	Extractor
DeepseekV3ForCausalLM	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Parametersparameter_count1

Claim history for Parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
1.03T	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Context windowcontext_length3

Claim history for Context window
Value	Valid from → to	Status	Source	Confidence	Extractor
262.1K tokens	12 Sept 2026 00:05 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic
256K tokens	11 Sept 2026 22:42 UTC → 12 Sept 2026 00:05 UTC	superseded	Artificial AnalysisT2	medium	deterministic
262.1K tokens	11 Sept 2026 21:10 UTC → 11 Sept 2026 22:42 UTC	superseded	OpenRouter public model & pricing listingT2	medium	deterministic

Max outputmax_output_tokens1

Claim history for Max output
Value	Valid from → to	Status	Source	Confidence	Extractor
100.3K tokens	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
Value	Valid from → to	Status	Source	Confidence	Extractor
Dec 2024	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Modalitiesmodalities1

Claim history for Modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Quantization formatquant_format1

Claim history for Quantization format
Value	Valid from → to	Status	Source	Confidence	Extractor
fp8	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

File sizefile_size_gb1

Claim history for File size
Value	Valid from → to	Status	Source	Confidence	Extractor
1029.2 GB	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
Value	Valid from → to	Status	Source	Confidence	Extractor
moonshotai/Kimi-K2-Instruct-0905	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
Value	Valid from → to	Status	Source	Confidence	Extractor
text-generation	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model cardmodel_card_url1

Claim history for Model card
Value	Valid from → to	Status	Source	Confidence	Extractor
https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Downloadsmetric.downloads1

Claim history for Downloads
Value	Valid from → to	Status	Source	Confidence	Extractor
37,069	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Likesmetric.likes1

Claim history for Likes
Value	Valid from → to	Status	Source	Confidence	Extractor
786	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Descriptiondescription1

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Gatedgated1

Claim history for Gated
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Hf inference providershf_inference_providers1

Claim history for Hf inference providers
Value	Valid from → to	Status	Source	Confidence	Extractor
featherless-ai, novita	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Is quantizedis_quantized1

Claim history for Is quantized
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Last modifiedlast_modified1

Claim history for Last modified
Value	Valid from → to	Status	Source	Confidence	Extractor
2026-01-30T04:50:25+00:00	11 Sept 2026 21:11 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Library namelibrary_name1

Claim history for Library name
Value	Valid from → to	Status	Source	Confidence	Extractor
transformers	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

License namelicense_name1

Claim history for License name
Value	Valid from → to	Status	Source	Confidence	Extractor
modified-mit	11 Sept 2026 22:27 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1

Claim history for Aa median output tokens per second
Value	Valid from → to	Status	Source	Confidence	Extractor
39.9	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
Value	Valid from → to	Status	Source	Confidence	Extractor
5,143,194	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Model typemodel_type1

Claim history for Model type
Value	Valid from → to	Status	Source	Confidence	Extractor
kimi_k2	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
Value	Valid from → to	Status	Source	Confidence	Extractor
moonshotai/kimi-k2-0905	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
Value	Valid from → to	Status	Source	Confidence	Extractor
4 Sept 2025	12 Sept 2026 04:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Reasoningreasoning1

Claim history for Reasoning
Value	Valid from → to	Status	Source	Confidence	Extractor
No	11 Sept 2026 22:42 UTC → current	current	Artificial AnalysisT2	medium	deterministic

Structured outputstructured_output1

Claim history for Structured output
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
frequency_penalty, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Tagstags1

Claim history for Tags
Value	Valid from → to	Status	Source	Confidence	Extractor
transformers, safetensors, kimi_k2, text-generation, custom_code, fp8	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

Tool callingtool_calling1

Claim history for Tool calling
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
Value	Valid from → to	Status	Source	Confidence	Extractor
BF16, F32, F8_E4M3	11 Sept 2026 21:50 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

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 5

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
OpenRouter public model & pricing listing	openrouter.ai/api/v1/models	catalogue	T2· Quality secondary	6 h ago	7
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/moonshotai/Kimi-K2-Instruct-0905/raw/main/README.md	model_card	T2· Quality secondary	8 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/moonshotai/Kimi-K2-Instruct-0905	model_page	T2· Quality secondary	9 h ago	4
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=moonshotai&p=0&sort=downloads	listing	T2· Quality secondary	9 h ago	6
Artificial Analysis	artificialanalysis.ai/leaderboards/models	leaderboard	T2· Quality secondary	13 h ago	1

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

Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →