System One models

AI decision models

A decision model answers typed questions about your input (yes or no, one option from a list, or a score) with a probability for every answer instead of written text. Compare every decision model Opper serves, from TypeSafe's Jev to Clef, Kev and the other open-source alternatives, and call any of them with one API key.

Get your API key
9 decision models12 routes9 providers5 run in the EU

Every decision model on Opper

Best JevMan score first. Each model shows who hosts it, where it runs and its cheapest price. Input runs from $0.02 to $0.24 per million tokens, and none of them bill output tokens.

Jev 1.13
by TypeSafe AI

Jev 1.13 is TypeSafe AI's System One model: it answers true/false, choice and rubric-score questions with calibrated probabilities instead of writing text.

Available on

TypeSafe AI
Pricing from$0.04/ 1M input$0/ 1M output64Kcontext

Privacy

ZDR
—Not established
Training
No
Region
Multi
GPT-6 Luna Decisions
by OpenAI

GPT-6 Luna Decisions is OpenAI's gpt-6-luna on its Decisions API: it answers predicate, choice and score questions about text and images with probabilities instead of writing text.

Available on

OpenAIUS
Pricing from$0.10/ 1M input$0/ 1M output

Privacy

ZDR
Training
No
Region
US
Clef-flash
by Cloudflare

Clef-flash, Cloudflare's fast 9B open-weight decision model, answers yes/no, choice and score questions about text or JSON with a probability for every option in tens of milliseconds.

Available on

BergetEUCloudflare
Pricing from$0.05/ 1M input$0/ 1M output66Kcontext

Privacy

ZDR
Training
No
Region
EU, Multi
Clef
by Cloudflare

Clef, Cloudflare's 27B open-weight decision model, answers yes/no, choice and score questions about text or JSON with a probability for every option instead of writing text.

Available on

CloudflareSferenceEU
Pricing from$0.24/ 1M input$0/ 1M output66Kcontext

Privacy

ZDR
Training
No
Region
Multi, EU
Microsoft Decision 1
by Microsoft

Fast decisions over text with calibrated probabilities for predefined answer options.

Available on

Azure
Pricing from$0.04/ 1M input$0/ 1M output33Kcontext

Privacy

ZDR
—Not established
Training
No
Region
Multi
Aplomb 1
by EmpirioLabs

Aplomb 1, EmpirioLabs' first model: a decision model that answers yes or no, choice and score questions about text, JSON, images, audio and video with calibrated probabilities, over a 1M-token state.

Available on

EmpirioLabs
Pricing from$0.02/ 1M input$0/ 1M output1Mcontext

Privacy

ZDR
Training
No
Region
Multi
Kev 4B
by Community

Kev 4B, Jared Palmer's open decision model fine-tuned from Alibaba's Qwen3.5-4B, answers yes/no, choice and score questions about text with calibrated probabilities instead of writing text.

Available on

OpperEU
Pricing from$0.04/ 1M input$0/ 1M output8Kcontext

Privacy

ZDR
Training
No
Region
EU
Laya
by Community

Laya, ConvAI Innovations' open encoder decision model, answers yes/no, choice and score questions about short text with calibrated probabilities in a single forward pass.

Available on

BergetEU
Pricing from$0.05/ 1M input$0/ 1M output512context

Privacy

ZDR
Training
No
Region
EU
Metis
by GreenPT

Joint decisions over shared state: yes/no, choice and score questions, with probabilities for every answer.

Available on

GreenPTEU
Pricing from$0.13/ 1M input$0/ 1M output16Kcontext

Privacy

ZDR
Training
No
Region
EU

Benchmarks

Each decision model we ran played 100 games of Pac-Man against the four arcade ghosts, ranked by mean score.

JevMan: the Pac-Man benchmark for AI decision models

JevMan: Jev 1.13's recorded gameWatch the top model's game
Top model in our runsJev 1.13
Models ranked8
Games per model100
  1. =1Jev 1.13
    2,750
  2. =1GPT-6 Luna Decisions
    2,568
  3. =1Clef-flash
    2,538
  4. 4Clef
    2,476
  5. 5Microsoft Decision 1
    2,390
  6. 6Aplomb 1
    1,693
  7. 7Kev 4B
    1,506
  8. 8Laya
    639

=1: Jev 1.13, GPT-6 Luna Decisions and Clef-flash are level within the margin of error.

See the JevMan benchmark →All decision benchmark gamesScores from Opper's own runs. Updated Oct 10, 2026.

Decision models vs LLMs

Both read your input. What comes back is different, and so is what you pay for.

ComparedDecision modelLLM
You sendA state (a ticket, a JSON object, a game board) and typed questions about itA prompt
You get backOne answer per question from the type you declared: yes or no (noul), one option from a list (choice) or a score, each with its probabilityGenerated text, or JSON when you ask for it
Your codeActs on the answer and sets a confidence threshold, with nothing to parseParses and validates the text
Billed on OpperInput tokens onlyInput and output tokens
Built forTriage, routing, moderation, guardrails, verification and game movesWriting, reasoning, tool use and conversation

Call any decision model through one API

Every decision model here answers the System One API at /v3/compat/v1/systemone and OpenAI's Decisions API format at /v3/compat/decisions, so moving from Jev to Kev or Clef is a change of model id. GPT-6 Luna Decisions runs natively on the Decisions format, with image input; the others are reached by translation.

Let your coding agent set it up

Paste this into Claude Code, Codex or Cursor.

Or call it yourself

curl https://api.opper.ai/v3/compat/v1/systemone \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "typesafe/jev-1.13.0",
    "state": "The customer cannot sign in and needs help immediately.",
    "questions": {
      "is_urgent": {
        "type": "noul",
        "instructions": "Does the customer need urgent help?"
      }
    }
  }'

Frequently asked questions

What is a decision model?

+
A decision model is an AI model that answers typed questions about an input instead of writing text. You send a state, such as a support ticket, a JSON object or a game board, with questions like "Is this urgent?" or "Which team owns it?", and it returns one answer per question in the type you declared (yes or no, one option from a list, or a score) with a probability for each option.

How is a decision model different from an LLM?

+
An LLM generates text token by token, which suits writing, reasoning and conversation. A decision model returns a typed answer and its probability, so your code can act on it directly and only trust answers above a confidence threshold. On Opper a decision model bills input tokens only.

What are System One models?

+
System One is the API TypeSafe built for Jev, and "System One models" is the name for decision models that answer it. On Opper every decision model answers the same System One endpoint: Jev 1.13, GPT-6 Luna Decisions, Clef-flash, Clef, Microsoft Decision 1, Aplomb 1, Kev 4B, Laya and Metis.

What are the alternatives to Jev?

+
GPT-6 Luna Decisions, Clef-flash, Clef, Microsoft Decision 1, Aplomb 1, Kev 4B, Laya and Metis all take the same requests as Jev 1.13 on Opper, so trying one is a change of model id. Clef-flash, Clef, Kev 4B and Laya publish their weights, which makes them the open-source Jev alternatives you can also run yourself: Kev 4B is Jared Palmer's fine-tune of Qwen3.5-4B-Base and Laya is ConvAI Innovations' 421M-parameter encoder under Apache-2.0. Jev vs. Kev, tested side by side

Which decision model is the best?

+
Of the 8 decision models we ran on JevMan, our Pac-Man benchmark, Jev 1.13 has the highest mean score (2,750), level within the margin of error with GPT-6 Luna Decisions and Clef-flash. The best one for you is the one that answers your own questions most accurately at a price and in a region that works for you, so run a few of them on the same requests before you pick. See the JevMan benchmark

Which decision models run in the EU?

+
Clef-flash, Clef, Kev 4B, Laya and Metis have routes hosted in Europe, run by Berget, Sference, Opper and GreenPT. Call one of those routes' model id and the request stays in Europe. Every EU-hosted model

How much does a decision model cost?

+
On Opper, decision models cost from $0.02 to $0.24 per million input tokens. None of them bill output tokens, so the price of a decision is the size of the state and the questions you send.

Can I use the OpenAI Decisions API through Opper?

+
Yes. Opper serves OpenAI's Decisions API format at /v3/compat/decisions for every decision model here, by its full model id. GPT-6 Luna Decisions runs natively there with text and image input; the others are reached by translation. The same models answer the System One format at /v3/compat/v1/systemone, so one piece of code can compare Jev, Clef, Kev and the rest.

Read this list from an agent

This list as data. The same models, prices and regions as markdown at opper.ai/models/decision-models.md.

The whole catalogue. The model catalogue is public JSON at https://api.opper.ai/v3/models, no API key needed. Filter it with query parameters, for example ?type=llm&limit=3, and page through it with limit and offset. Use it when you can fetch a URL but cannot connect to an MCP server. Coding agents that use MCP can connect to https://api.opper.ai/mcp. Two of the server's tools need no account and no sign-in: list_models searches the model catalogue by name, type, provider or capability, and get_guide returns short setup guides. Everything that touches your account needs you to approve the connection in the browser first. About the MCP server

Run every decision model on one key

Try Jev, Clef, Kev and the rest on the same requests, then keep the one that fits your questions, your budget and where your data may go.

Get startedView Documentation