# Jev 1.13

Decision models · checked 2026-10-14 · https://dbggr.dev/models/jev/

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
- Docs: https://docs.typesafe.ai/models

## 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](https://typesafe.ai/blog/introducing-system-one-models-and-jev) |

## 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](https://benchmarkheaven.com/jev-models) |
| JevBench time | 0.24 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | [Independent](https://benchmarkheaven.com/jev-models) |
| 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

| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Jev 1.13 | $0.042 | 77.1 | Closed |
| [Clef](https://dbggr.dev/models/clef/) | $0.24 | 75.3 | Open |
| [d1](https://dbggr.dev/models/d1/) | $0.04 | 74.4 | Closed |
| [OpenAI Decisions (GPT-6 Luna)](https://dbggr.dev/models/openai-decisions/) | $0.10 | 73.5 | Closed |
| [Microsoft-Decision-1](https://dbggr.dev/models/microsoft-decision-1/) | $0.042 | 70.8 | Closed |
| [Clef-flash](https://dbggr.dev/models/clef-flash/) | $0.038 | 63.8 | Open |
| [Clef-omni](https://dbggr.dev/models/clef-omni/) | $0.15 | 58.3 | Open |
| [d1-3B](https://dbggr.dev/models/d1-3b/) | Self-host | 49.5 | Open |
| [d1-omni-600M (experimental)](https://dbggr.dev/models/d1-omni-600m/) | Self-host | 32.8 | Open |
| [Laya](https://dbggr.dev/models/laya/) | Free | 32.5 | Open |
| [CLM-8B](https://dbggr.dev/models/clm-8b/) | Self-host | 20.1 | Open |
| [Strands Decider 2B](https://dbggr.dev/models/strands-decider-2b/) | Self-host | – | Open |

## 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.