# Jev

Jev is TypeSafe AI's System One decision model: it evaluates a state against typed yes/no, choice, and score questions and returns calibrated probabilities and confidence instead of generated text. It is built for routing, classification, guardrails, and scoring steps that need a fast, structured judgment your code can act on directly. Its published context window is 32,000 tokens. The advertised input rate is $0.042 per million input tokens. The advertised output rate is $0.00 per million output tokens.

- Model identifier: ` typesafe-ai/jev `
- Creator: TypeSafe AI
- Providers: TypeSafe AI
- Model type: Evaluation
- Canonical model page: [Jev](<https://impossibl.com/typesafe-ai/jev>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-09-15

## Providers

TypeSafe AI hosts Jev. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

| Provider | Endpoint location | Routes | Verified context window | Tool calling |
| --- | --- | --- | --- | --- |
| TypeSafe AI | Not specified | 1 | Not verified | Not supported |

The model price applies whichever provider serves the request. Endpoint locations do not guarantee inference residency.

## Specs and Capabilities

- Context window: 32,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text
- Outputs: typed answers with probabilities
- Tool calling: Not supported

## API access

Use ` typesafe-ai/jev ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/systemone `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.042 | per million input tokens |
| Output | $0.00 | per million output tokens |
| Cache read | Not published | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Jev?

Jev is TypeSafe AI's System One decision model: it evaluates a state against typed yes/no, choice, and score questions and returns calibrated probabilities and confidence instead of generated text. It is built for routing, classification, guardrails, and scoring steps that need a fast, structured judgment your code can act on directly.

Sources: [TypeSafe AI API reference](<https://docs.typesafe.ai/api>); [Introducing System One models and Jev](<https://typesafe.ai/blog/introducing-system-one-models-and-jev>)

### How much does Jev cost?

Jev costs $0.042 per million input tokens and $0.00 per million output tokens through the Impossibl API. All rates are in USD.

### What is the context length of Jev?

Jev has a 32,000-token context window through the Impossibl API.

### Does Jev support tool calling?

No. Jev does not support tool calling through the Impossibl API.

### What inputs and outputs does Jev support?

Jev accepts text as input. Jev returns typed answers with probabilities.

### How do I use Jev through an API?

Jev is available through the Impossibl API. Use typesafe-ai/jev as the model identifier with /v1/systemone. The quickstart explains how to create an API key and send your first request.

### When was Jev released?

TypeSafe AI released Jev on September 15, 2026.

Sources: [Creator release announcement](<https://typesafe.ai/blog/introducing-system-one-models-and-jev>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Jev: model details and pricing](<https://impossibl.com/typesafe-ai/jev>)
- [Model directory](<https://impossibl.com/models>)
- [TypeSafe AI API reference](<https://docs.typesafe.ai/api>)
- [Introducing System One models and Jev](<https://typesafe.ai/blog/introducing-system-one-models-and-jev>)