Model tracker / Decision models / TypeSafe AI
Jev 1.13
Jev 1.13 is a closed decision model from TypeSafe AI: it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. It costs $0.042 per million input tokens (TypeSafe API, OpenRouter, Vercel AI Gateway), and output is free. It scores 77.1 on the independent JevBench Capability Score (board v1.7.46), where it is the reference system.
- Made by
- TypeSafe AI
- Weights
- Closed
- Size
- Undisclosed
- Where
- TypeSafe API, OpenRouter, Vercel AI Gateway
- Images
- No, text only
- Context
- 64K per request
- Fine-tuning
- None offered
Jev 1.13 price
US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.
| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| TypeSafe API, OpenRouter, Vercel AI Gateway | $0.042 | Free | Output is free. | 2026-10-14 |
Jev 1.13 benchmarks
| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 77.1 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | Independent |
| JevBench time | 0.24 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
| Reported speed | 70–500 ms end to end | Latency on the maker's own hardware | TypeSafe AI |
Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.
Decision models like Jev 1.13
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Jev 1.13 | $0.042 | 77.1 | Closed |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| d1 Liquid AI | $0.04 | 74.4 | Closed |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Microsoft-Decision-1 Microsoft | $0.042 | 70.8 | Closed |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | Free | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Jev 1.13 on dbggr
- Haiku 5.5 and four-cent decision models: the AI price war reaches the bottom tier Saturday edition, 2026-10-10
- Microsoft enters decision models at Jev's price as TypeSafe raises $870M Daily, 2026-10-09
- Google launches the Gemini agent, one work agent that also runs Claude models Daily, 2026-10-08
- Claude Haiku 5.5 launches at $0.10 per million tokens, matching GPT-6 Luna Daily, 2026-10-07
- OpenAI publishes 722 AI-written math papers, claiming proofs of the quasi-Riemann hypothesis and Unique Games Daily, 2026-10-06
- Containing agents stopped being the labs' private problem Saturday edition, 2026-10-03
- Stop asking your LLM multiple-choice questions: a guide to decision models Article, 2026-10-02
- Cloudflare and AWS release open-weight decision models to rival Jev Daily, 2026-10-01
Jev 1.13 FAQ
How much does Jev 1.13 cost?
Jev 1.13 costs $0.042 per million input tokens at TypeSafe API, OpenRouter, Vercel AI Gateway. Output is free. Checked 14 October 2026.
Is Jev 1.13 open weight?
No. Jev 1.13 is only available through TypeSafe API, OpenRouter, Vercel AI Gateway.
How fast is Jev 1.13?
TypeSafe AI reports 70–500 ms end to end, measured on its own hardware. JevBench gives 0.24 seconds per decision, measured end to end.