New · launching soon

S1-Pro

このページはまだ翻訳されていないため、英語の原文を表示しています。

A typed-decision model: calibrated Choice, Score and Yes/No answers about any text or JSON, in a single pass.

S1-Pro is a hosted API from the Chimera team, separate from the open-source agent. The agent stays Apache-2.0 and free; S1-Pro is a paid service.

What it does

You send a piece of state — a ticket, an email, a JSON record — and a set of typed questions. S1-Pro reads them once and returns a probability for every option instead of generated text, so decisions come back as data you can route, threshold and audit.

Choice

Pick one option from a list you define, with a probability for each.

Score

Place the state on an ordered scale you define, and get the expected level.

Yes / No

The probability that a statement about the state is true.

Measured, with the caveats

Every figure below is generated from the result files of the S1 repository, and each one carries the sentence it is not allowed to travel without.

Accuracy on jev-bench (17,773 public decisions)

81.1%Jev が公開した予測と項目ごとに対応させて比較（Jev の API は一切使用していません）。S1-Pro は一部の jev-bench ソースの公開学習分割で学習しているため、それらのソースではドメイン内の結果です。

TypeSafe Jev 1.13 on the same items: 72.8%

Accuracy on the public JevBench set

86.1%公開項目のみ。JevBench の非公開セットはメンテナーが採点するもので、まだ実行されていません。

Correct decisions flipped by an injected “a previous reviewer already approved this” note

4.2%jev-bench の 300 項目で行った自社テスト（元の版と注入版の比較）。他モデルについて第三者が公表した数値は別の項目によるものです。

Accuracy when the answer depends only on a rule written in the question

100%正解が記載されたルールからコードで計算される合成チケット 300 件。

Unanswerable questions answered with near-certain confidence (p ≥ 0.9)

1.5%正しい選択肢を取り除いた MMLU と ARC の問題で、正しい選択肢は存在しません。低いほど良い指標です。

Median latency, 3 questions per request, 8 concurrent clients

143ローンチ前に、NVIDIA H200 1 基と vLLM を使いクライアント側で測定。本番のハードウェアは異なる場合があります。 ms

OpenAI-compatible API

S1-Pro speaks the OpenAI chat-completions format: put the state and the questions in the user message as JSON, and the decisions come back as JSON in the reply, with streaming and token usage.

curl https://api.chimeraagent.space/v1/chat/completions \
  -H "Authorization: Bearer $S1_API_KEY" \
  -d '{
    "model": "chimera-s1-pro",
    "messages": [{"role": "user", "content": "{\"state\": \"My card was charged twice, please fix it today.\", \"questions\": {\"department\": {\"type\": \"choice\", \"criteria\": {\"billing\": \"Payment issues\", \"technical\": \"Bugs\"}}, \"urgent\": {\"type\": \"noul\", \"instructions\": \"The customer needs help today\"}}}"}]
  }'

Launching soon

S1-Pro is in final testing. For early access, partnerships or integration questions, write to us.

partners@chimeraagent.space