---
title: "What is Decider v1.1: a decision model that returns a choice, a score, or a probability | system-one.dev"
description: "Decider v1.1 is a decision model. It does not generate text. It returns a choice, a score, or a yes/no probability. See what it can do in an agent, and how it compares with Jev. Sign in to try live."
canonical: "https://system-one.dev/en/models/decider-v1-1"
language: "en"
---

# Decider

Reads text and JSON and returns a choice, a score, or a yes/no answer.

Decider v1.1 is a decision model provided by system-one.dev. Give it text or JSON and a few questions (pick one, score, or yes/no); it returns a choice, a score, or a yes/no probability and does not generate text. It does not accept images.

Call it with the TypeScript SDK or the API and send the full model ID. Billing is in credits; the rate is in Model info on this page. Sign in to try live: [Try live (sign in required)](https://system-one.dev/en/demo).

To learn what this kind of model is, see “[What is a decision model?](https://system-one.dev/en/blog/what-is-a-decision-model)”


## Model info

- Provided by: system-one.dev
- 1 credit per question per 4KB
- Up to 32 questions · 64KB per request
- Inputs: text and JSON
- Pick one: up to 255 options; Score: 2–10 levels
- Released 2026-10-07

## Uses

- **Tool routing**: Pick one candidate tool, or decide that none of them fit. See [Agent tool routing](https://system-one.dev/en/blog/agent-tool-routing).
- **Model routing**: First judge how hard the request is, then send it to a small or large model. See [Model routing](https://system-one.dev/en/blog/model-routing).
- **First-pass evaluation**: Use Score against a rubric instead of an LLM as judge. See [Using Score instead of an LLM as judge](https://system-one.dev/en/blog/llm-as-a-judge-alternative).
- **Completion checks**: Use a yes/no probability to decide whether an agent is done. See [When an agent should stop](https://system-one.dev/en/blog/agent-stop-condition).
- **Guardrails**: Judge whether input or output breaks a rule, then allow, block, or hand off. See [Agent guardrails](https://system-one.dev/en/blog/agent-guardrails).
- **Try it**: [Tweet moderation demo](https://system-one.dev/en/demo/tweet-moderation), [Phishing-email demo](https://system-one.dev/en/demo/phishing-email) (sample data; sign in to try live).

## Frequently asked questions

### Is Decider a large language model?

No. It does not write a reply or explain its reason. You ask a few questions and it only returns a choice, a score, or a probability. Use a generative model when you need written content.

### How is Decider different from Jev?

Both models accept only text and JSON, and the request format is the same. The main difference is the rate; see each page’s Model info. To see which works better, swap the model ID on the same data. Details: [Jev model page](https://system-one.dev/en/models/jev).

### Does Decider support Chinese?

Test Chinese results with your own data first.

### How is it billed?

By credits: every 4KB is one block, and a partial block still counts as one. Cost = blocks × questions × the model rate. See Model info on this page. Details: [Pricing](https://system-one.dev/en/pricing).

### How do I choose Decider?

Send the full model ID in the request. If you omit it, the default model is used. The model ID is in Model info on this page.

### Can I try it live?

Yes. [Try live (sign in required)](https://system-one.dev/en/demo).

Last updated 2026-10-12

- [Open GET /v1/models](https://system-one.dev/v1/models)

- [Developer docs](https://docs.system-one.dev/en/docs/api#developer-details)

- [Try live (sign in required)](https://system-one.dev/en/demo)

- [All models](https://system-one.dev/en/models)