llm-semantic-router/Decision-1.0-Eos-0.8B

[image]

Decision-1.0-Eos-0.8B

Eos — the dawn of a clearer decision.

Open Decision Foundation Models

Turn context into choices, judgments, and scores. Eos reads your questions and candidate descriptions, then returns structured answers with probability distributions. Ask many questions about one context, or apply the same questions across a batch of contexts.

Decision collection · Get started · Architecture

Measured decisions

61.89 overall — ahead of all four reference models on the same 54-task benchmark.

3,766 scored questions; fixed task weights and the same requests for every model. Overall weights are 30% / 25% / 15% / 15% / 15%. Both Laya references use their released general weights. ¹Qwen uses the benchmark's fixed decision-letter readout. This is an observed regression benchmark; overall leadership does not imply a win on every task. Full 54-task matrix, intervals, and method.

Built for responsive decisions

14.7–21.3% lower latency with growing context. The qualified AMD ROCm runtime accelerates Eos without changing model weights or decision probabilities. Short-input latency stays within 1% of the previous runtime in this measurement.

[image]

Measured local SystemOne requests, batch size 8; network and Studio excluded. Latency tables, runtime coverage and method.

Your questions define the task

Use the System One request format: state / model / questions → answers. Candidate descriptions are supplied at runtime. The Python API supports both shared-context questions and multi-context batches.

Official SDK and curl examples · Batch decisions · Input and runtime requirements

Use

Replace the placeholder with a SystemOne-compatible endpoint configured to serve Decision-1.0-Eos-0.8B, and set DECISION_API_KEY to that endpoint's key.

pip install typesafe-sdk

import os
from typesafe_sdk import TypeSafeClient, Choice, Noul

client = TypeSafeClient(
    api_key=os.environ["DECISION_API_KEY"],
    base_url="https://your-decision-endpoint.example",
    model="Decision-1.0-Eos-0.8B",
)
questions = {
    "route": Choice(instructions="Which team should handle this request?",
                    criteria={"delivery": "Damaged or missing parcels", "billing": "Payments and invoices"}),
    "urgent": Noul(instructions="Does the customer request action today?"),
}
response = client.system_one(state="The parcel arrived damaged. Please send a replacement today.", questions=questions)
print(response.choices["route"].choice, response.nouls["urgent"].noul)

The same request with curl:

curl -X POST https://your-decision-endpoint.example/v1/systemone \
  -H "Authorization: Bearer $DECISION_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "Decision-1.0-Eos-0.8B",
    "state": "The parcel arrived damaged. Please send a replacement today.",
    "questions": {
      "route": {"type": "choice", "instructions": "Which team should handle this request?", "criteria": {"delivery": "Damaged or missing parcels", "billing": "Payments and invoices"}},
      "urgent": {"type": "noul", "instructions": "Does the customer request action today?"}
    }
  }'

Official Python SDK · HTTP API · Usage and deployment details

Built to decide

[image]

A 24-layer hybrid decoder combines gated linear attention and full attention. A shared decision head reads candidate endpoints against a global query representation and scores all candidates in one forward pass per question batch.

The released inference model contains the text backbone and decision head. See the architecture and readout diagrams for the computation graph.

Built on Qwen3.5-0.8B. English and Chinese are represented in the release evaluation. Transfer, candidate-carried evidence, and some rule tasks remain areas for improvement; probabilities can be overconfident. Complete-input limits and verified runtime behavior are documented in USAGE.md.

Inference validation · License · Attribution · Evaluation evidence