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.
Primitives
Section titled “Primitives”Every question in a request uses one of three primitives, and every answer returns a constrained, schema-valid distribution:
| Primitive | Question asks | Answer fields | Maps in code to |
|---|---|---|---|
choice | Which of these named options (up to 255)? | choice, probabilities, confidence, mouse | switch / router |
noul | Is this binary condition true? | noul (0.0 to 1.0), mouse | if / gate |
score | Which of these 2–10 ordered rubric levels applies? | score, legend, probabilities, confidence, mouse | threshold / 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:
statetokens 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 viaPOST /v1/calibrationsso every answer includesmouse.abstain(truewhen 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: noneandCache-Control: no-store. Request states, questions, answers, and calibration examples are never logged or stored.
Endpoints
Section titled “Endpoints”Base URL: https://api.mouse.dev (US-East)
| Method & path | Description |
|---|---|
POST /v1/decisions | Evaluate choice, noul (yes/no), and score questions in parallel against a state. |
POST /v1/calibrations | Fit a signed confidence cutoff profile (calp1.) on 200–400 labeled examples using 5-fold out-of-fold cross-fitting. |
GET /v1/models | List immutable model snapshots (mouse-preview-2026-10-13) and active aliases (mouse-1, mouse). |
GET /healthz | Unauthenticated liveness and region probe. |
Example request
Section titled “Example request”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?" } } }'Example response
Section titled “Example response”{ "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}Next steps
Section titled “Next steps”- Quickstart — Create an API key and run your first multi-question call in 60 seconds.
- Build with coding agents — Copy one prompt to deploy
mouse-1using Cursor, Claude Code, or Codex, or point your agent at/llms-full.txtand/llm.txt. - API Reference — Complete request schemas, answer shapes, headers, and status codes.
- Question types — Learn how
choice,noul, andscoremap to control flow and howconfidenceis calculated. - Migrate from Jev or OpenAI Decisions — Side-by-side comparison and migration recipes.
- Console Playground — Test states and questions interactively in your browser.