Jev vs OpenAI Decisions API

What OpenAI announced

From the DevDay 2026 recap:

Decisions API enables real-time decision-making by focusing Luna's intelligence on a specific set of user-defined questions with finite pre-defined answers. Developers supply context using text or images, and get back answers they can use to classify content, route requests, or choose an agent's next action. Available in limited preview today with a broad release planned in the coming days.

Primary launch posts:

• @OpenAIDevs — Luna, finite answers, classify / route / agent next action, limited preview
• @thsottiaux — constrained decisions, visual inputs, less than a few hundreds of milliseconds end to end

Secondary explainers (not OpenAI docs): Firecrawl comparison, Vercel explainer

What Jev is

TypeSafe's Jev is a decision model (System One), not a chat model that happens to pick a label. Launched September 15, 2026.

• Question types: Choice, Score, Noul (mixable in one call)
• Returns: per-option probabilities and confidence
• Input: text only (string, JSON object, or array of strings)
• API: documented POST /v1/systemone with Python and JavaScript SDKs
• Pricing: $0.042 per million input tokens, output free
• Limits: 64k tokens per request; 32k for state plus longest question

Sources: TypeSafe models, llms.txt

Side by side

Facts only. When OpenAI has not published a detail, that is what the table says.

What builders should do

1. If you need vision tomorrow (screenshots, UI state, computer-use frames): Decisions is the documented fit once you have preview/GA access. Until then, preprocess to text (OCR / DOM / captions) and keep shipping on Jev.
2. If you need calibrated gates (confidence thresholds, Score, multi-question fan-out): Jev's published surface is the control plane you can write policy against today.
3. If you need GA with no waitlist: Jev. Decisions FOMO is real on X; shipping is better marketing than waiting.
4. If you're building demos: put the answer space on the card. OpenAI's whole pitch is finite options. Make the option list visible on madewithjev builds so visitors instantly get the category.
5. Name collision: OpenRouter already branded a “Decisions API” path that can serve Jev. Say OpenAI Decisions vs OpenRouter Decisions vs TypeSafe System One / Jev so readers don't fuse three products.

How to talk about timing

Jev mid-September, Decisions at DevDay, then Cloudflare / Perplexity / AWS decision-shaped products. OpenAI has not said they copied anyone. Frame it as category validation: the industry agrees branching on generative prose was the wrong default for classify / route / act.

Builds that show the job

Routing, classification, and agent next action — with the cost and latency each builder published.

Duncan

@ephraimduncan

Built a model router with Jev by @typesafeai. Jev decides what model fits your request best and the request is sent to that model.

X·Routing and model choice

A model router on Jev

Gregor Zunic

@gregpr07

Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

X·Search

Pick

Flight search with Browser Use

Run time

~7 s

Cost

~$0.004

tamara

@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

X·Context and memory

Pick

Instant compaction for Claude

Hassan

@nutlope

I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on http://1kpapers.com The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live: http://1kpapers.com

Live site·Documents and OCR

1kpapers

Documents

1,018 papers

Total cost

$0.08

Median latency

256 ms

More on Jev use cases.

Try it today

Next steps

• OpenAI Decisions alternatives — who should use Jev instead, and when Decisions still wins
• How to use Jev — your first call, SDKs, and gateways
• Jev pricing — what a decision costs across real builds
• Jev vs an LLM — same job both ways, with published numbers
• Agent prompts — wire Jev into Claude Code, Cursor, Codex

Common questions

What is OpenAI's Decisions API?

A constrained decision-making API on GPT-6 Luna. You define questions and finite answer options; it picks one using text or image context. Announced at DevDay 2026 for classify, route, and agent next action jobs. Currently in limited preview.

How is Jev different from OpenAI Decisions?

Jev is generally available with a documented API (POST /v1/systemone), three question types (Choice, Score, Noul), per-option probabilities and confidence scores, and published pricing ($0.042/M input tokens, output free). Decisions is in limited preview with no public schema or pricing as of late September 2026.

Is OpenAI Decisions generally available?

No. As of late September 2026, it is in limited preview with a broad release planned. Access is for selected API customers.

Does OpenAI Decisions support images?

Yes. OpenAI states developers can supply context using text or images. Jev takes text only (strings, JSON, or arrays). For visual input, builders preprocess with OCR or a vision model first.

Does Jev return probabilities and confidence?

Yes. Every Choice answer includes a probability for each option and a confidence score. Your code can act on confident answers automatically and escalate the rest. OpenAI has not published whether Decisions returns probabilities; some press claims exist but are not in official docs as of September 30, 2026.

Which should I use for agent routing today?

If you need vision (screenshots, UI state), wait for Decisions access or preprocess to text. If you need calibrated confidence thresholds, multi-question batching, or GA access today, use Jev. For both text-based routing and GA availability, Jev is documented and ready.