Skip to content
Get API key

Overview

mouse-1 is a decision model built for agent harnesses and AI-powered software. Instead of generating text token by token and parsing prose back into control flow, it reads your state and evaluates up to 128 typed questions in one request, scoring each option directly instead of generating text, and returns a calibrated probability distribution across your options in ~100 ms.

Keep control flow, deterministic rules, and side effects in your application code. Call mouse-1 at narrow decision points where your system needs programmable common sense over unstructured text or structured program state.

Every question in a request uses one of three primitives, and every answer returns a constrained, schema-valid distribution:

PrimitiveQuestion asksAnswer fieldsMaps in code to
choiceWhich of these named options (up to 255)?choice, probabilities, confidence, mouseswitch / router
noulIs this binary condition true?noul (0.0 to 1.0), mouseif / gate
scoreWhich of these 2–10 ordered rubric levels applies?score, legend, probabilities, confidence, mousethreshold / rank key

Every question in a single POST /v1/decisions call is evaluated in parallel and in isolation against the same state:

  • Speculative fan-out is nearly free: state tokens are billed once per request regardless of how many questions you attach. Ask every question a downstream branch might need and let your code ignore the rest.
  • No cross-question contamination: Adding or removing a question never shifts another question's probabilities.
  • Calibrated abstention: Fit a signed calp1. profile on 200+ of your own labeled examples via POST /v1/calibrations so every answer includes mouse.abstain (true when top probability falls below the out-of-fold cutoff for your target error rate).
  • Zero data retention by default: Every request sends Mouse-Data-Retention: none and Cache-Control: no-store. Request states, questions, answers, and calibration examples are never logged or stored.

Base URL: https://api.mouse.dev (US-East)

Method & pathDescription
POST /v1/decisionsEvaluate choice, noul (yes/no), and score questions in parallel against a state.
POST /v1/calibrationsFit a signed confidence cutoff profile (calp1.) on 200–400 labeled examples using 5-fold out-of-fold cross-fitting.
GET /v1/modelsList immutable model snapshots (mouse-preview-2026-10-13) and active aliases (mouse-1, mouse).
GET /healthzUnauthenticated liveness and region probe.

This single request routes an agent turn across four tools (choice) and checks whether a proposed shell command is safe to run without human approval (noul):

curl https://api.mouse.dev/v1/decisions \
-H "Authorization: Bearer $MOUSE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mouse-1",
"state": {
"task": "Rename exported function `parseToken` to `verifyToken` in src/auth.ts.",
"proposed_command": "pnpm --filter @mouse/relay test"
},
"questions": {
"next_tool": {
"type": "choice",
"instructions": "Which tool should handle `task` next?",
"criteria": {
"edit_file": "Modify source code in a file",
"grep_search": "Search for symbols across the repository",
"run_tests": "Execute the test suite",
"ask_user": "Ask the user for clarification"
}
},
"safe_to_run": {
"type": "noul",
"instructions": "Is `proposed_command` safe to run without human approval?"
}
}
}'
{
"id": "dec_8f92a1c04e1b902d",
"object": "systemone.response",
"model": "mouse-preview-2026-10-13",
"answers": {
"next_tool": {
"type": "choice",
"choice": "edit_file",
"confidence": 0.88,
"probabilities": {
"edit_file": 0.91,
"grep_search": 0.06,
"run_tests": 0.02,
"ask_user": 0.01
},
"mouse": {
"calibrated": false,
"p_top": 0.91,
"abstain": null
}
},
"safe_to_run": {
"type": "noul",
"noul": 0.98,
"mouse": {
"calibrated": false,
"p_top": 0.98,
"abstain": null
}
}
},
"usage": {
"input_tokens": 74,
"state_tokens": 26,
"question_tokens": 26,
"framing_tokens": 22,
"image_tokens": 0,
"output_tokens": 0,
"cost_usd": 0.0000074
},
"latency_ms": 38.2
}