rebuilt the X algorithm with Jev - uses real weights - simulates virality of your post - has a global feed (you see everyone) it's insanely accurate
Primitives
Primitive limits
The hard caps to design around: 255 Choice options, 2 to 10 Score levels, and a 64k context covering state plus questions.
- Category
- Primitives
- Also known as
- —
- Related terms
- 5
- Directory entries
- 3
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Choice accepts a maximum of 255 options; Score accepts at least two and at most ten levels; the context window is 64k tokens for state plus all questions, with 32k for state plus the single longest question. Choice and Score answers carry confidence, while Noul returns only the probability.
The limits shape common patterns: very large candidate sets get pre-filtered or searched in two passes, and Score levels are kept few and well separated because they are weak at numeric calibration.
Tagsprimitivesapilimits
Related terms
Definitions that connect to this one.
ChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.PrimitivesContext windowThe 64k-token budget covering state plus all questions, with a 32k sub-budget for state plus the longest question.API & ModelsLine-by-line searchRank every line of a document in one request with a Choice, while a Noul checks whether the document contains an answer at all.PatternsScore levelOne entry in a Score's ordered criteria list; levels are numbered by array position from 0 and judged independently.Primitives
From the directory
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Sites & GuidesDocs#official#docs#api
Official
The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.
Sites & GuidesDocs#official#docs#models
Official
Semantic search over GitHub's Terms of Service: one request ranks all 218 lines with a Choice while a Noul checks whether the document contains an answer at all, including when it should say no.
Cookbooks & DemosDocs#official#cookbook#search
Official
From the community
Posts from builders shipping with Jev right now.
The X algorithm, rebuilt with Jev
Hard-coded rules moved to Jev
Now using @typesafeai Jev in aiseotracker.com, linkdr.com, genppt.com, etc AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast! Also for regular LLM Show more
A chief of staff for bots
got @typesafeai's new model Jev as a chief of staff for bots Jev reads the task, wakes the right teammates off the bench and gives each one the right model It is possible on OpenMausBot as it supports all the LLMs from your existing subscriptions Jev as a decision engine is Show more
Hide posts on X in plain language
I built a browser extension with Jev @typesafeai that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.
$10,000 in Jev’s hands
I gave Jev $10,000 and let it trade
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Jev plays Slay the Spire 2
昨天出的 typesafe.ai Jev 模型 适合高频决策，那岂不又是适合打游戏？ 之前用 GPT-6 Astra 代打杀戮尖塔2 能力强但速度慢。 我刚实测用 Jev 打，行动思考只需 0.7秒， 画面我都没看清它就操作完了。 这超人类游戏速度， 着实又让我震惊瘫坐了😅 语言很难描述这感觉，看视频⬇️
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x