The AI map · Models and assistants

Decision models

Models that answer typed questions about a situation with a choice, a score or a probability your code can use directly, instead of writing text. The ones that lead it as of 29 October 2026.

  1. Jev New since July

    TypeSafe AI

    A model that takes program state plus typed questions and returns a choice or score with calibrated probabilities, for routing, triage, guardrails and game or browser agents.

    Pick it Your software needs many fast yes/no, pick-one or score decisions, and you do not need any text back.

    Price $0.042 per million input tokens; output tokens free

    Source: docs.typesafe.ai

  2. Decisions API (on GPT-6 Luna) New since July

    OpenAI

    An OpenAI endpoint that returns a probability, a choice from a fixed set, or a score against a rubric, about 10 times faster than the Responses API.

    Pick it You already build on OpenAI and want classification, routing or prioritising without parsing generated text.

    Price Runs on gpt-6-luna; Luna lists at $0.10 per million input tokens and $0.50 per million output

    Source: developers.openai.com

What changed

  1. 14 Oct 2026 TypeSafe released Jev 1.14, now the default jev-latest model, at the same price. docs.typesafe.ai
  2. 9 Oct 2026 TypeSafe AI raised a Series A of $870 million at a $7.5B valuation, led by Andreessen Horowitz. typesafe.ai
  3. 29 Sep 2026 OpenAI announced the Decisions API, built on GPT-6 Luna, at DevDay; its docs now say it is generally available. openai.com
  4. 15 Sep 2026 TypeSafe AI came out of stealth with a $40M seed led by DCVC and released Jev, which it calls the first public System One model. finance.yahoo.com

Questions people ask about it

AI in Your Product

  1. Should my startup add AI features, and which ones actually matter to users?
  2. How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)?
  3. How much does it cost to run AI features, and how do I keep costs sane?
  4. Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in?
  5. How do I test whether my AI feature actually works before launch (evals, in plain terms)?
  6. How do I stop my AI feature from making things up in front of customers?

AI Agents

  1. What actually is an AI agent, in plain language?
  2. Why would a founder use agents instead of a chatbot or automation?
  3. What real tasks are founders delegating to agents today?
  4. How do I build my first agent without being technical?
  5. Which platform or framework should I build my agents on?
  6. How much do AI agents cost to run, and how do I keep the bill under control?

The rest of the map

Checked 29 October 2026. Prices and rankings move every few months; each tool links the page its claims were read from.

eChai Partner Brands The partnership →