MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905 · Moonshot AINot yet established

Tokenizer group (measured): Moonshot AI
Evidence confidence: Moderate
Declared tokenizer tag: Other
Entered catalogue: 4 September 2025
Last tested: 3 September 2026
Measurement: Measured

Evidence

✓ near-exact agreement (49/50) with moonshotai/kimi-k2.6

Compare with MoonshotAI: Kimi K2.6

Download JSON Report a correction

Identity statement

MoonshotAI: Kimi K2 0905 is Moonshot AI's model, and its measured tokenizer sits in Moonshot AI's own signature group alongside its sibling models. No other maker's measured model shares it so far.

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Clean measurement; no exact match yet	tk_f14a0fdd
API surface	No other entry shares this exact contract	api_87b94582
Context and output	262,144 context · 98,304 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	Novita	measured 3 September 2026

Closest measured models

Agreement across the mutually clean test strings

MoonshotAI: Kimi K2.6moonshotai/kimi-k2.649/50 · 98%MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking49/50 · 98%MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code49/50 · 98%MoonshotAI: Kimi K2.5moonshotai/kimi-k2.547/48 · 98%MoonshotAI: Kimi K3moonshotai/kimi-k340/49 · 82%MoonshotAI: Kimi K2 0711moonshotai/kimi-k238/50 · 76%

Click a row to open the full comparison.

The measured fingerprint

Marginal prompt-token cost of each test string, grouped by script

All 50 rows

English and whitespace

en-prose14

en-long16

spaces-203

spaces-603

tabs-204

newlines-204

mixed-ws6

Digits

digits-93

digits-124

digits-3010

digits-sep7

float-long9

CJK

zh-common9

zh-long10

zh-rare18

ja-kana11

ja-kanji14

ko13

Other scripts

ru16

ar15

he16

hi17

th21

el22

Emoji

emoji-basic10

emoji-skin20

emoji-zwj-family11

emoji-zwj-x333

emoji-flags14

emoji-prof20

Rare Unicode

math26

boxdraw24

combining14

cjk-ext-b16

surrogates31

zalgo36

rtl-mix8

Code

py-code25

py-indent15

json20

html16

regex43

camel6

snake6

Repetition and encodings

rare-word-x531

repeat-tok41

base6431

hex11

url17

uuid27

An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 9 prompt tokens.

Declared record

What the catalogue claims about this model

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...

Modalities: text->text
Declared tokenizer: Other
Prompt price: $0.60 / M tokens
Completion price: $2.50 / M tokens

Supported parameters

frequency_penaltymax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

defaults: {}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

4 September 2025Enters the OpenRouter catalogue with no declared family.
3 September 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
3 September 2026YFarmX assessment: consistent with the Moonshot AI family, moderate confidence.

Cite this page as the evidence record for MoonshotAI: Kimi K2 0905: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.