TypeSafe: Jev 1.13
typesafe/jev-1.13 · TypeSafeNot yet established- Declared family
- Unknown
- Evidence confidence
- Unknown
- Declared tokenizer tag
- Other
- Entered catalogue
- 18 September 2026
- Last tested
- 18 September 2026
- Measurement
- Measured
AI Desk · Model IdentityNew arrival
Identity statement
TypeSafe: Jev 1.13 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_5e398719 |
| API surface | No other entry shares this exact contract | api_08d46e60 |
| Context and output | 32,000 context · 28,800 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | TypeSafe | measured 18 September 2026 |
Closest measured models
Agreement across the mutually clean test stringsTencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct24/50 · 48%Tencent: Hy-MT2-7Btencent/hy-mt2-7b24/50 · 48%Poolside: Laguna XS 2.1poolside/laguna-xs-2.121/50 · 42%OpenAI: GPT-5 Nanoopenai/gpt-5-nano20/50 · 40%OpenAI: gpt-oss-20bopenai/gpt-oss-20b20/50 · 40%OpenAI: gpt-oss-120bopenai/gpt-oss-120b20/50 · 40%
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-prose15
en-long18
spaces-203
spaces-603
tabs-203
newlines-205
mixed-ws6
Digits
digits-99
digits-1212
digits-3030
digits-sep12
float-long22
CJK
zh-common18
zh-long24
zh-rare20
ja-kana16
ja-kanji15
ko15
Other scripts
ru30
ar26
he23
hi24
th26
el28
Emoji
emoji-basic10
emoji-skin20
emoji-zwj-family11
emoji-zwj-x333
emoji-flags16
emoji-prof20
Rare Unicode
math31
boxdraw27
combining5
cjk-ext-b13
surrogates40
zalgo35
rtl-mix12
Code
py-code25
py-indent15
json25
html16
regex44
camel10
snake6
Repetition and encodings
rare-word-x541
repeat-tok22
base6435
hex17
url22
uuid36
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 273 prompt tokens.
Declared record
What the catalogue claims about this modelTypeSafe's first System One model: a structured decision model that takes a piece of state plus typed questions and returns calibrated probabilities. Served on OpenRouter's decisions route rather than chat completions.
- Modalities
- text->decisions
- Declared tokenizer
- Other
- Prompt price
- $0.04 / M tokens
- Completion price
- $0 / M tokens
Supported parameters
History
Every observation, kept as taken- 18 September 2026Enters the OpenRouter catalogue with no declared family.
- 18 September 2026Fingerprinted in the YFarmX catalogue sweep · 50 of 50 strings measured clean.
Cite this page as the evidence record for TypeSafe: Jev 1.13: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
CompareCompare now