Meituan: LongCat 2.0
meituan/longcat-2.0 · MeituanNot yet established- Declared family
- Unknown
- Evidence confidence
- Unknown
- Declared tokenizer tag
- Other
- Entered catalogue
- 20 July 2026
- Last tested
- 21 August 2026
- Measurement
- Measured
Identity statement
Meituan: LongCat 2.0 has a clean measured fingerprint that currently sits alone: no other measured model shares its signature.
Evidence stack
Signals of different kinds, weighed together| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Clean measurement; no exact match yet | tk_c670dac9 |
| API surface | No other entry shares this exact contract | api_f7ac75a7 |
| Context and output | 1,048,756 context · 262,144 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | AtlasCloud | measured 21 August 2026 |
Closest measured models
Agreement across the mutually clean test stringsLing-3.0-flashinclusionai/ling-3.0-flash27/50 · 54%inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash27/50 · 54%inclusionAI: Ring-2.6-1Tinclusionai/ring-2.6-1t27/50 · 54%inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t27/50 · 54%Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-2026042013/27 · 48%Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct23/50 · 46%
Click a row to open the full comparison.
The measured fingerprint
Marginal prompt-token cost of each test string, grouped by scriptAll 50 rows
English and whitespace
en-prose14
en-long17
spaces-203
spaces-603
tabs-204
newlines-204
mixed-ws6
Digits
digits-99
digits-1212
digits-3030
digits-sep12
float-long22
CJK
zh-common9
zh-long10
zh-rare18
ja-kana9
ja-kanji10
ko17
Other scripts
ru15
ar14
he29
hi34
th26
el27
Emoji
emoji-basic10
emoji-skin14
emoji-zwj-family10
emoji-zwj-x330
emoji-flags16
emoji-prof18
Rare Unicode
math31
boxdraw24
combining13
cjk-ext-b16
surrogates40
zalgo36
rtl-mix11
Code
py-code25
py-indent15
json25
html16
regex45
camel6
snake6
Repetition and encodings
rare-word-x531
repeat-tok41
base6435
hex18
url19
uuid36
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 14 prompt tokens.
Declared record
What the catalogue claims about this modelLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
- Modalities
- text->text
- Declared tokenizer
- Other
- Prompt price
- $0.30 / M tokens
- Completion price
- $1.20 / M tokens
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p
defaults: {}
History
Every observation, kept as taken- 20 July 2026Enters the OpenRouter catalogue with no declared family.
- 21 August 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
Cite this page as the evidence record for Meituan: LongCat 2.0: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.