New · launching soon

S1-Pro

Esta página todavía no está traducida, así que estás leyendo el original en inglés.

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%Emparejado, ítem por ítem, con las predicciones publicadas de Jev; no se usó ninguna API de Jev. S1-Pro se entrenó con los splits públicos de entrenamiento de algunas fuentes de jev-bench, así que en esas fuentes el resultado es dentro del dominio.

TypeSafe Jev 1.13 on the same items: 72.8%

Accuracy on the public JevBench set

86.1%Solo los ítems públicos. El conjunto sellado de JevBench lo evalúan sus mantenedores y aún no se ha ejecutado.

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

4.2%Prueba propia sobre 300 ítems de jev-bench, versión limpia frente a inyectada. Las cifras de terceros para otros modelos usaron ítems distintos.

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

100%300 tickets sintéticos cuya respuesta correcta se calcula por código a partir de la regla declarada.

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

1.5%Preguntas de MMLU y ARC sin la opción correcta, así que ninguna opción es válida. Cuanto menor, mejor.

Median latency, 3 questions per request, 8 concurrent clients

143Medido desde el cliente en una NVIDIA H200 con vLLM, antes del lanzamiento. El hardware de producción puede ser distinto. 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