New · launching soon

S1-Pro

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%Paired, item by item, against Jev's published predictions — no Jev API was used. S1-Pro was trained on the public train splits of some jev-bench sources, so on those sources this is an in-domain result.

TypeSafe Jev 1.13 on the same items: 72.8%

Accuracy on the public JevBench set

86.1%Public items only. The sealed JevBench set is scored by its maintainers and has not been run yet.

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

4.2%Our own test on 300 jev-bench items, clean versus injected. Figures reported by third parties for other models used different items.

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

100%300 synthetic tickets whose correct answer is computed by code from the stated rule.

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

1.5%MMLU and ARC questions with the correct option removed, so no option is right. Lower is better.

Median latency, 3 questions per request, 8 concurrent clients

143Measured from the client on one NVIDIA H200 with vLLM, before launch. Production hardware may differ. 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