Last verified: .How we rank
OpenAI announced Decisions API in public beta with a Luna-class decision model priced per million input tokens in community posts. It targets the same engineering pain as Jev: software needs scored options, not essays. Beta terms, model names, and regional availability can change quickly.
Our snapshot does not list OpenAI on the public Decision Index board, so treat accuracy claims as vendor-beta until you run your own eval harness.
jev.aitools.fyi is an independent directory. We are not TypeSafe, Cloudflare, OpenAI, Perplexity, or the makers named on this page unless a listing is marked official.
Catalog listing: OpenAI Decisions API (brand-focused page; this article is the Jev comparison).
OpenAI Decisions API vs Jev at a glance
| Topic | OpenAI Decisions API | TypeSafe Jev | Source |
|---|---|---|---|
| Maker | OpenAI | TypeSafe AI | OpenAI community: Decisions API beta |
| First public release | Public beta announced 2026 (community post) | Hosted System One (ongoing) | OpenAI Decisions API beta announcement |
| License / access | not published | Hosted API (weights not downloadable) | OpenAI community: Decisions API beta |
| Hosted price (input) | gpt-6-luna (vendor, beta): $0.10 per M input tokens (vendor list, 2026-10-12) | $0.042 per M input tokens (vendor list, 2026-10-12) | TypeSafe models page (jev-1.13.0 price table) |
| API shape | Decisions API (beta) separate from chat completions | POST /v1/systemone | OpenAI Decisions API beta post; Jev: TypeSafe API reference |
| Question types | Structured decision objects (vendor beta docs) | Choice, Score, Noul | OpenAI Decisions API beta post |
| Inputs | Vendor JSON schema for decisions | Structured state string | OpenAI Decisions API beta post |
| Model sizes | not published | Hosted Jev (closed) | OpenAI community: Decisions API beta |
| Latency | not published | not published | OpenAI community: Decisions API beta (no published p95 SLA cited) |
| Decision Index (public) | Not listed on Decision Index public board for this edition | 60.11 (Decision Index 0.3.1, snapshot 2026-10-10; independent harness, not vendor-only) | Decision Index 0.3.1 public snapshot |
| Data handling | Processed under OpenAI enterprise / API terms | Processed under TypeSafe terms | OpenAI privacy policy |
| SDKs | OpenAI SDK routes for beta endpoints | typesafe_sdk, gateways, MCP ecosystem | OpenAI Decisions API beta post |
| Adoption signal | not published | not published | OpenAI community: Decisions API beta |
What Decisions API is
OpenAI announced Decisions API in public beta with a Luna-class decision model priced per million input tokens in community posts. It targets the same engineering pain as Jev: software needs scored options, not essays. Beta terms, model names, and regional availability can change quickly.
Our snapshot does not list OpenAI on the public Decision Index board, so treat accuracy claims as vendor-beta until you run your own eval harness.
Accuracy and benchmarks
Independent Decision Index edition 0.3.1 does not list OpenAI Decisions API in the snapshot we ship.
Fit and tradeoffs
Choose Decisions API when your constraints match its deployment model: OpenAI is already your primary AI vendor with approved DPAs; You want decisions beside GPT-class tools under one invoice; You can accept beta churn on model names and limits.
Pricing and ops
Decisions API beta pricing in community posts is per-million input tokens; confirm enterprise list price in your OpenAI account before finops sign-off.
Migrating from hosted Jev
Keep your question map and threshold logic stable. Swap client configuration to point at the new base URL or SDK, then run shadow traffic until disagreement rates fall below your risk budget.
// Before: hosted Jev
const client = new TypeSafe({ apiKey: process.env.TYPESAFE_API_KEY });
await client.systemone({ model: "jev-latest", state, questions });
// After: self-hosted System One compatible server (Kev, decider, SemIf, etc.)
const client = new TypeSafe({ baseURL: "http://localhost:8000" });
await client.systemone({ model: "gpt-6-luna", state, questions });
Ecosystem links
Anchor on the Decisions API beta announcement and OpenAI privacy policy, then read hosted Jev facts when you need an open-weight exit ramp.
Product-specific notes
Decisions API is a beta surface: model codenames, regional availability, and enterprise DPAs can change without a semver bump on your side. Request payloads resemble System One questions, but error shapes and rate limits follow OpenAI's general API policies.
If you already route chat through OpenAI, adding Decisions can reduce vendor count, but you lose the open-weight exit ramp Kev or Laya provide. Community beta posts cite pricing; your enterprise agreement may override list numbers shown in our facts table.
OpenAI does not appear on the public Decision Index board we import, so plan an internal eval harness before accuracy promises. Data handling follows OpenAI's standard API terms unless your account team signs a custom addendum.
When to choose OpenAI Decisions API
- OpenAI is already your primary AI vendor with approved DPAs
- You want decisions beside GPT-class tools under one invoice
- You can accept beta churn on model names and limits
When to stay on Jev
- You need System One primitives documented on docs.typesafe.ai today
- You rely on Vercel AI Gateway typesafe-ai/jev routing
- You want public Decision Index scores for procurement
FAQ
- Is OpenAI Decisions API the same product as TypeSafe Jev?
No. Jev is TypeSafe's hosted System One service. OpenAI Decisions API is a separate product with its own weights, terms, and ops model unless explicitly documented as compatible HTTP.
- Does OpenAI Decisions API beat Jev on Decision Index?
OpenAI Decisions API is not listed on the Decision Index snapshot we import; run your own eval.
- Can I use the TypeSafe SDK with OpenAI Decisions API?
OpenAI's beta announcement is the source we link for API shape; plan a staging adapter to map errors and fields before you route production gates through gpt-6-luna.
- Should I leave hosted Jev entirely?
Not necessarily. Teams often keep Jev for gates that need vendor support while experimenting with OpenAI Decisions API on lower-risk paths. Run shadow mode until metrics prove parity.
Other Jev alternatives
Jev alternatives hub
Ranked table and quick picks
Cloudflare Clef vs Jev
Clef and Clef-flash are Cloudflare's Apache-2.0 decision models with a Jev-compatible API. Compare price, context, speed…
Kev as a Jev alternative
Kev is an open Jev-like model family on Qwen with a System One compatible server. Compare sizes, hardware, accuracy, lic…
Perplexity pplx-decider as a Jev alternative
pplx-decider is Perplexity's Apache-2.0 27B decision model, hosted or self-run. Compare Decision Index scores, price, ha…
Sources
Last verified . Spotted an error? Contact us.